INDEX

Explanations

proper nouns related to politics

oai_token-act-pair · gpt-3.5-turbo

quantitative data and statistics related to events or entities

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

 Citiz

-0.59

pat

-0.55

illance

-0.54

 mechanics

-0.53

 outs

-0.53

 visitation

-0.53

 environmental

-0.52

 telecommunications

-0.51

 scares

-0.51

 gull

-0.51

POSITIVE LOGITS

optional

0.79

=-=-

0.75

unknown

0.74

estyles

0.73

OTAL

0.73

Loading

0.72

trak

0.72

Optional

0.71

milo

0.67

ãĤ´ãĥ³

0.66

Activations Density 0.553%

proper nouns related to politics

quantitative data and statistics related to events or entities

No Comments

No Known Activations