INDEX

Explanations

phrases related to problem-solving or decision-making

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "figure" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ibaba

-0.84

-0.74

rem

-0.66

nor

-0.64

rons

-0.63

ewitness

-0.63

VIDEO

-0.63

rary

-0.61

ription

-0.60

riott

-0.60

POSITIVE LOGITS

 prominently

0.84

out

0.80

 skating

0.80

istically

0.73

omething

0.66

matically

0.65

heads

0.64

ħ

0.62

sonian

0.62

how

0.60

Activations Density 0.033%

phrases related to problem-solving or decision-making

occurrences of the word "figure" and its variations

No Comments

No Known Activations