INDEX

Explanations

phrases related to involvement or participation in various activities or events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "involved."

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

\\\\\\\\

-0.64

omach

-0.62

ander

-0.62

ãĥ©ãĥ³

-0.62

 Gleaming

-0.61

Float

-0.60

ipples

-0.59

 testament

-0.59

umb

-0.59

flu

-0.58

POSITIVE LOGITS

ioned

0.89

enza

0.86

cius

0.85

itaire

0.73

involved

0.72

asive

0.68

ive

0.67

 involved

0.66

enne

0.64

ional

0.64

Activations Density 0.044%

phrases related to involvement or participation in various activities or events

instances of the word "involved."

No Comments

No Known Activations