INDEX

Explanations

instances where a decision is being discussed

oai_token-act-pair · gpt-3.5-turbo

references to decisions made in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

icas

-0.72

vae

-0.71

ingers

-0.68

icum

-0.66

 havoc

-0.66

 tert

-0.65

ubric

-0.64

aband

-0.64

 Offense

-0.63

uction

-0.63

POSITIVE LOGITS

 makers

1.04

 maker

0.87

makers

0.81

maker

0.81

making

0.79

jar

0.79

 ACTIONS

0.75

 taken

0.72

 decision

0.72

to

0.72

Activations Density 0.048%

instances where a decision is being discussed

references to decisions made in various contexts

No Comments

No Known Activations