INDEX

Explanations

instances of apologies or requests for apologies in text

oai_token-act-pair · gpt-3.5-turbo

words related to apologies and expressions of remorse

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

weeney

-0.88

arnaev

-0.80

picking

-0.76

marked

-0.75

population

-0.73

markets

-0.72

::::::::

-0.71

growth

-0.70

aic

-0.66

ulhu

-0.65

POSITIVE LOGITS

 apologized

0.97

 apology

0.94

 unres

0.93

 apologize

0.91

 apologised

0.89

giving

0.88

 apologizing

0.85

 apologies

0.84

 forgiveness

0.81

 apologise

0.81

Activations Density 0.027%

instances of apologies or requests for apologies in text

words related to apologies and expressions of remorse

No Comments

No Known Activations