INDEX

Explanations

prominent figures in various fields, such as politics, religion, and academia

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "prominent" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ope

-0.84

ework

-0.82

eries

-0.78

opes

-0.76

ramid

-0.74

thur

-0.74

Phones

-0.74

agan

-0.73

fest

-0.73

yrinth

-0.73

POSITIVE LOGITS

 personalities

0.87

 figures

0.82

 role

0.77

 roles

0.76

 prominent

0.75

 commentator

0.72

 finan

0.72

 endors

0.72

 endorsements

0.71

 contender

0.71

Activations Density 0.040%

prominent figures in various fields, such as politics, religion, and academia

occurrences of the word "prominent" and its variations

No Comments

No Known Activations