INDEX

Explanations

phrases related to experiences or actions during specific periods of time

oai_token-act-pair · gpt-3.5-turbo

phrases related to someone's work or time spent at specific locations

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

ptoms

-0.75

usra

-0.74

zers

-0.74

ickr

-0.70

ANT

-0.70

riber

-0.68

antine

-0.68

lement

-0.67

rist

-0.66

endi

-0.66

POSITIVE LOGITS

 stint

0.88

 captivity

0.84

 lowly

0.73

 surfing

0.73

 Gain

0.69

 academia

0.66

 exile

0.65

 consecutive

0.65

 accrued

0.65

 mining

0.65

Activations Density 0.376%

phrases related to experiences or actions during specific periods of time

phrases related to someone's work or time spent at specific locations

No Comments

No Known Activations