INDEX

Explanations

past tense verbs indicating actions or events that have occurred

oai_token-act-pair · gpt-3.5-turbo

past participles or actions related to processes or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 secretaries

-0.67

 integration

-0.61

 referrals

-0.59

 landlords

-0.59

 recruitment

-0.59

 uncanny

-0.58

 chapters

-0.57

 chiefs

-0.57

 endorsements

-0.57

POSITIVE LOGITS

by

0.99

 correctly

0.85

 safely

0.80

 anew

0.79

 alive

0.79

});

0.78

 cheaply

0.78

 properly

0.78

 successfully

0.78

 incorrectly

0.77

Activations Density 0.310%

past tense verbs indicating actions or events that have occurred

past participles or actions related to processes or states

No Comments

No Known Activations