INDEX

Explanations

mentions of coordinated efforts or actions involving multiple parties

oai_token-act-pair · gpt-3.5-turbo

terms related to organized collective efforts, especially in political or social contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 mates

-0.94

iddles

-0.88

ometers

-0.84

onyms

-0.84

verbs

-0.84

forts

-0.83

anders

-0.82

stories

-0.80

keys

-0.79

anguages

-0.79

POSITIVE LOGITS

 effort

1.59

 initiative

1.29

 investigation

1.23

 endeavor

1.18

 crackdown

1.18

 attempt

1.18

 campaign

1.16

 consortium

1.12

 boycott

1.12

 coalition

1.12

Activations Density 0.250%

mentions of coordinated efforts or actions involving multiple parties

terms related to organized collective efforts, especially in political or social contexts

No Comments

No Known Activations