INDEX

Explanations

words related to different scenarios or locations

oai_token-act-pair · gpt-3.5-turbo

references to various forms of narratives or ongoing stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ople

-0.69

 Moonlight

-0.66

 Concord

-0.65

Gameplay

-0.60

 Clubs

-0.59

 Entered

-0.58

 Leth

-0.57

 Highlights

-0.56

 Mono

-0.56

Eng

-0.56

POSITIVE LOGITS

worldly

0.99

 besides

0.82

 than

0.81

 outing

0.81

bender

0.77

imester

0.74

anche

0.73

blow

0.72

rant

0.71

roller

0.71

Activations Density 0.256%

words related to different scenarios or locations

references to various forms of narratives or ongoing stories

No Comments

No Known Activations