INDEX

Explanations

single words related to accountability and responsibility

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a high degree of intensity or categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 sculpt

-0.84

 grouping

-0.78

 camp

-0.78

 orchestr

-0.76

 ones

-0.74

 negoti

-0.73

 shuff

-0.72

 regener

-0.72

 placement

-0.72

 engineering

-0.72

POSITIVE LOGITS

Advertisements

1.43

Comment

1.41

Translation

1.36

RAW

1.35

Related

1.35

Posted

1.35

Read

1.34

About

1.30

Original

1.28

RELATED

1.28

Activations Density 0.291%

single words related to accountability and responsibility

phrases indicating a high degree of intensity or categorization

No Comments

No Known Activations