INDEX

Explanations

phrases indicating future events or actions by the speaker

oai_token-act-pair · gpt-3.5-turbo

repeated use of the pronoun 'we' indicating collective experiences or actions

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

 Creation

-0.62

REDACTED

-0.62

 externalToEVAOnly

-0.59

forms

-0.58

 prescribing

-0.57

 totality

-0.57

ãĤ¯

-0.57

 Substance

-0.57

 suicide

-0.56

 Publication

-0.56

POSITIVE LOGITS

ibo

1.00

athered

1.00

igh

0.97

asel

0.94

've

0.94

ighed

0.94

arily

0.94

'll

0.92

IRD

0.91

blogs

0.90

Activations Density 0.212%

phrases indicating future events or actions by the speaker

repeated use of the pronoun 'we' indicating collective experiences or actions

No Comments

No Known Activations