INDEX

Explanations

words related to poor quality or negative aspects

oai_token-act-pair · gpt-3.5-turbo

negative descriptors related to poor quality or unpleasant experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

encers

-0.96

Topics

-0.87

arians

-0.86

icity

-0.84

itsch

-0.84

ership

-0.83

iers

-0.83

heny

-0.83

ais

-0.79

inion

-0.78

POSITIVE LOGITS

 horrible

0.94

 crappy

0.90

 shitty

0.90

 miserable

0.81

 nightmare

0.79

 horribly

0.79

 bastard

0.77

 goddamn

0.76

 crap

0.76

 fucking

0.75

Activations Density 0.016%

words related to poor quality or negative aspects

negative descriptors related to poor quality or unpleasant experiences

No Comments

No Known Activations