INDEX

Explanations

places or locations and their descriptions

oai_token-act-pair · gpt-3.5-turbo

references to places and their characteristics

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

obin

-0.82

redo

-0.77

verse

-0.72

pair

-0.71

gey

-0.70

genic

-0.69

 phrases

-0.67

 particles

-0.66

é»Ĵ

-0.66

MEP

-0.66

POSITIVE LOGITS

 reopened

1.05

tyard

1.02

 renovation

1.02

 staffed

1.00

 Located

0.97

 renovations

0.94

 housed

0.92

Located

0.91

 renovated

0.88

 emptied

0.86

Activations Density 0.834%

places or locations and their descriptions

references to places and their characteristics

No Comments

No Known Activations