INDEX

Explanations

phrases indicating fairness or honesty

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing fairness, honesty, and clarity in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 surf

-0.73

med

-0.64

edu

-0.62

Build

-0.61

ãĥĺ

-0.60

 seams

-0.59

ãĥĲ

-0.58

 Written

-0.58

 satur

-0.57

bern

-0.57

POSITIVE LOGITS

ensional

0.75

 Opinion

0.75

idge

0.72

ohn

0.72

oops

0.70

Ans

0.69

ayson

0.69

ESCO

0.69

Obj

0.68

 Philippe

0.67

Activations Density 0.080%

phrases indicating fairness or honesty

phrases emphasizing fairness, honesty, and clarity in discussions

No Comments

No Known Activations