INDEX

Explanations

instances where the word "Everybody" is mentioned

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Everybody" 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 @ 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

eda

-0.91

ean

-0.90

aic

-0.86

ea

-0.73

rd

-0.72

ester

-0.71

ult

-0.71

hor

-0.71

sequ

-0.70

 Hastings

-0.69

POSITIVE LOGITS

selves

0.89

 else

0.85

 nodd

0.82

THING

0.81

 wanna

0.71

 answ

0.70

WAYS

0.70

bags

0.69

 Royale

0.68

cipline

0.67

Activations Density 0.025%

instances where the word "Everybody" is mentioned

occurrences of the word "Everybody" and its variations

No Comments

No Known Activations