INDEX

Explanations

instances where the "chance" to do something is mentioned

oai_token-act-pair · gpt-3.5-turbo

instances of the word "chance"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DCS

-0.83

Chief

-0.71

aida

-0.70

Traditional

-0.69

rete

-0.67

oper

-0.66

Supported

-0.66

Wan

-0.66

anity

-0.65

lisher

-0.65

POSITIVE LOGITS

llor

1.33

 chance

0.86

ller

0.81

 Rouhani

0.77

fir

0.74

 opportunity

0.74

 Encounter

0.72

finder

0.72

chance

0.69

 encounter

0.69

Activations Density 0.026%

instances where the "chance" to do something is mentioned

instances of the word "chance"

No Comments

No Known Activations