INDEX

Explanations

references to images or photographs

oai_token-act-pair · gpt-3.5-turbo

references to images in the text

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

oler

-0.82

acity

-0.77

sole

-0.76

 consolid

-0.74

izons

-0.73

rency

-0.71

oser

-0.69

acious

-0.68

odox

-0.68

lease

-0.67

POSITIVE LOGITS

 Provided

1.01

 Â©

0.92

\/\/

0.86

 Photograph

0.82

HAEL

0.81

0.80

 Getty

0.80

 IMAGES

0.77

Pic

0.74

Bry

0.74

Activations Density 0.031%

references to images or photographs

references to images in the text

No Comments

No Known Activations