INDEX

Explanations

names of people or characters along with actions and descriptions related to them

oai_token-act-pair · gpt-3.5-turbo

numerical values associated with measurements or statistics

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

 censored

-0.76

 oppressed

-0.74

 tram

-0.74

 incarn

-0.73

 regener

-0.72

 censor

-0.72

 ninja

-0.71

 endeav

-0.71

 painfully

-0.70

 regenerate

-0.70

POSITIVE LOGITS

Newsletter

1.49

Contribut

1.44

Asked

1.40

RELATED

1.38

Refer

1.34

Related

1.34

Another

1.33

Topics

1.33

About

1.31

Meanwhile

1.31

Activations Density 0.299%

names of people or characters along with actions and descriptions related to them

numerical values associated with measurements or statistics

No Comments

No Known Activations