INDEX

Explanations

mentions of specific types of animals, particularly foxes

oai_token-act-pair · gpt-3.5-turbo

references to foxes

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

assy

-0.76

apter

-0.70

 contrace

-0.69

rians

-0.67

 Edison

-0.67

 Carmen

-0.65

 Commonwealth

-0.65

 Lumpur

-0.64

rella

-0.64

 inval

-0.62

POSITIVE LOGITS

conn

1.29

es

0.96

holes

0.93

hole

0.86

haw

0.85

esy

0.82

eur

0.82

croft

0.81

worthy

0.81

Activations Density 0.032%

mentions of specific types of animals, particularly foxes

references to foxes

No Comments

No Known Activations