INDEX

Explanations

mentions of the word "sap"

oai_token-act-pair · gpt-3.5-turbo

references to "sap" and related contexts in various discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

eering

-0.93

ated

-0.72

swick

-0.69

âĸ¬âĸ¬

-0.67

hift

-0.65

DOM

-0.65

ãĥĦ

-0.65

teen

-0.63

eer

-0.63

inline

-0.62

POSITIVE LOGITS

Sap

1.47

sap

1.43

ience

0.98

utics

0.87

olicy

0.86

ient

0.86

utical

0.86

osit

0.83

apers

0.81

iped

0.80

Activations Density 0.013%

mentions of the word "sap"

references to "sap" and related contexts in various discussions

No Comments

No Known Activations