INDEX

Explanations

statements that involve evaluation, opinion, or summaries of a situation

oai_token-act-pair · gpt-3.5-turbo

phrases related to connections and relationships between people or groups

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cooldown

-0.55

externalActionCode

-0.53

 presidency

-0.52

 predecessor

-0.48

 doesnt

-0.47

washer

-0.46

ishable

-0.46

availability

-0.45

isSpecialOrderable

-0.44

til

-0.44

POSITIVE LOGITS

 themselves

1.13

selves

0.87

their

0.85

 their

0.83

 collectively

0.82

 THEIR

0.78

Their

0.70

 Their

0.67

 apiece

0.65

 alike

0.64

Activations Density 1.395%

statements that involve evaluation, opinion, or summaries of a situation

phrases related to connections and relationships between people or groups

No Comments

No Known Activations