INDEX

Explanations

references to neighborhoods, neighbors, and community settings

oai_token-act-pair · gpt-3.5-turbo

mentions of neighborhoods and related community terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 bearer

-0.78

udeb

-0.74

OPLE

-0.72

othal

-0.70

ISM

-0.69

ocobo

-0.66

"]=>

-0.66

REDACTED

-0.66

ONT

-0.66

lain

-0.66

POSITIVE LOGITS

bors

1.47

 Neigh

1.27

Neigh

1.14

bour

1.10

 neighbour

1.08

 neighbors

1.04

 neighbours

1.03

 neighbor

0.99

bor

0.94

 neighb

0.92

Activations Density 0.006%

references to neighborhoods, neighbors, and community settings

mentions of neighborhoods and related community terms

No Comments

No Known Activations