INDEX

Explanations

text related to criticizing, commenting, or making negative evaluations about various topics or individuals

oai_token-act-pair · gpt-3.5-turbo

the word "about" and its related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

OGR

-0.87

hesis

-0.86

rift

-0.81

quez

-0.80

chnology

-0.77

KC

-0.72

hiba

-0.72

ÂłÂłÂłÂł

-0.71

à¥

-0.69

waters

-0.69

POSITIVE LOGITS

how

0.97

 whether

0.90

 reforming

0.79

 respecting

0.74

why

0.74

 resolving

0.73

 improving

0.72

 migrating

0.70

 changing

0.70

 overcoming

0.70

Activations Density 0.125%

text related to criticizing, commenting, or making negative evaluations about various topics or individuals

the word "about" and its related contexts

No Comments

No Known Activations