INDEX

Explanations

words related to locations or hotspots

oai_token-act-pair · gpt-3.5-turbo

terms related to hotspots or areas of heightened activity or significance

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

ned

-0.78

ŃĶ

-0.73

Drag

-0.70

ress

-0.69

smanship

-0.68

 Rape

-0.68

 Clown

-0.67

amination

-0.65

aughs

-0.64

^^^^

-0.61

POSITIVE LOGITS

pots

1.19

pot

1.07

 Hots

0.92

pur

0.89

combe

0.87

 hots

0.85

bsite

0.83

erver

0.83

pring

0.82

atile

0.81

Activations Density 0.054%

words related to locations or hotspots

terms related to hotspots or areas of heightened activity or significance

No Comments

No Known Activations