INDEX

Explanations

future tense actions or plans

oai_token-act-pair · gpt-3.5-turbo

the word "gonna" and its variations, indicating future intentions or actions

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

rehens

-0.78

template

-0.76

mere

-0.74

amped

-0.74

controlled

-0.72

Newsletter

-0.69

cius

-0.69

crafted

-0.68

ament

-0.67

enthal

-0.66

POSITIVE LOGITS

be

0.94

 lose

0.91

 give

0.89

go

0.88

get

0.87

nab

0.86

 stick

0.85

 snag

0.85

eat

0.84

 buckle

0.83

Activations Density 0.010%

future tense actions or plans

the word "gonna" and its variations, indicating future intentions or actions

No Comments

No Known Activations