INDEX

Explanations

lines related to movie titles and release information

oai_token-act-pair · gpt-3.5-turbo

phrases and punctuation associated with film releases and discussions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 arsen

-0.73

xon

-0.72

hap

-0.70

hod

-0.70

 fiat

-0.69

icons

-0.69

oros

-0.69

 Ples

-0.66

ioned

-0.64

swer

-0.64

POSITIVE LOGITS

 Remastered

0.97

feat

0.92

 soundtrack

0.87

 starring

0.85

 anthology

0.84

 Volume

0.84

ebted

0.81

 lyrics

0.79

 finale

0.79

 Season

0.77

Activations Density 0.352%

lines related to movie titles and release information

phrases and punctuation associated with film releases and discussions

No Comments

No Known Activations