INDEX

Explanations

words related to sensory experiences, particularly scents and sounds

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "of" with varying frequencies, indicating a focus on possession or association

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orthy

-0.87

imens

-0.80

igun

-0.78

ials

-0.70

ESA

-0.70

employ

-0.69

wcs

-0.69

VP

-0.68

OPLE

-0.68

ISC

-0.67

POSITIVE LOGITS

 darkness

0.82

 Darkness

0.75

 heaven

0.74

 Nanto

0.73

 truth

0.72

 light

0.71

 sunlight

0.68

 unbeliev

0.68

 desperation

0.68

 doom

0.67

Activations Density 0.242%

words related to sensory experiences, particularly scents and sounds

phrases that include the word "of" with varying frequencies, indicating a focus on possession or association

No Comments

No Known Activations