INDEX

Explanations

phrases starting with "In a statement" and "said in a statement"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "statement."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

avorite

-0.77

elsius

-0.73

upiter

-0.72

skill

-0.68

cffff

-0.68

vag

-0.68

animate

-0.63

rentice

-0.62

existent

-0.62

azes

-0.62

POSITIVE LOGITS

 statement

0.99

 announcing

0.87

 emailed

0.84

Statement

0.83

 issued

0.78

ariat

0.77

 apologizing

0.77

 thanking

0.74

atures

0.73

 released

0.70

Activations Density 0.029%

phrases starting with "In a statement" and "said in a statement"

occurrences of the word "statement."

No Comments

No Known Activations