INDEX

Explanations

references to fuel or fuel-related terms

oai_token-act-pair · gpt-3.5-turbo

references to fuel-related topics or concepts

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

å¥³

-0.81

onyms

-0.74

ettings

-0.72

lihood

-0.72

umbn

-0.72

iannopoulos

-0.70

orld

-0.70

ordan

-0.69

Bei

-0.69

sonian

-0.66

POSITIVE LOGITS

 rods

0.88

less

0.85

 fuel

0.84

fuel

0.82

 combustion

0.82

 fumes

0.82

wagon

0.81

 fueling

0.81

plug

0.80

train

0.79

Activations Density 0.033%

references to fuel or fuel-related terms

references to fuel-related topics or concepts

No Comments

No Known Activations