INDEX

Explanations

locations or establishments with the term "centre" in their names

oai_token-act-pair · gpt-3.5-turbo

references to places or institutions related to a central theme or topic

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

 VIDEOS

-0.81

 Tanz

-0.70

 Gott

-0.68

 Lieberman

-0.66

RESULTS

-0.65

earable

-0.65

 Dull

-0.65

Shot

-0.64

stein

-0.63

clerosis

-0.63

POSITIVE LOGITS

 analyse

0.83

piece

0.78

 Whilst

0.78

ablishment

0.77

colour

0.77

 Firstly

0.76

uminium

0.72

 defences

0.72

forth

0.71

Â£

0.70

Activations Density 0.219%

locations or establishments with the term "centre" in their names

references to places or institutions related to a central theme or topic

No Comments

No Known Activations