INDEX

Explanations

words related to baking or cooking

oai_token-act-pair · gpt-3.5-turbo

segments of text related to specific labels or categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Day

-0.79

Inc

-0.78

Rac

-0.76

 Cove

-0.76

 Ranked

-0.74

 Disorder

-0.70

 Poll

-0.70

 Shades

-0.69

 Year

-0.69

 Parks

-0.69

POSITIVE LOGITS

iest

1.21

liest

1.06

osphere

1.02

hest

1.01

 portion

0.91

 hypothesis

0.90

agonist

0.89

omial

0.85

ultimate

0.85

ciation

0.85

Activations Density 0.492%

words related to baking or cooking

segments of text related to specific labels or categorization

No Comments

No Known Activations