INDEX

Explanations

words related to apologies

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "apologize" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

marked

-0.83

weeney

-0.81

jun

-0.73

corn

-0.73

aida

-0.69

VEN

-0.68

picking

-0.67

tail

-0.67

vet

-0.66

aic

-0.65

POSITIVE LOGITS

 apologised

1.06

 apologized

1.04

 apologize

1.02

 apologise

1.00

 apology

0.96

 apologizing

0.92

 unres

0.88

 apologies

0.82

 thanking

0.78

 forgiveness

0.77

Activations Density 0.011%

words related to apologies

occurrences of the word "apologize" and its variations

No Comments

No Known Activations