INDEX

Explanations

words related to the film industry, specifically focusing on motion pictures

oai_token-act-pair · gpt-3.5-turbo

references to the term "motion" in various contexts

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

rosso

-0.82

aez

-0.71

iott

-0.69

oys

-0.68

dds

-0.68

iders

-0.67

vae

-0.64

inia

-0.63

 Province

-0.63

arding

-0.63

POSITIVE LOGITS

 motion

0.98

motion

0.92

Motion

0.91

 Motion

0.89

 sickness

0.88

 blur

0.88

 motions

0.84

 Picture

0.80

Animation

0.78

immune

0.76

Activations Density 0.027%

words related to the film industry, specifically focusing on motion pictures

references to the term "motion" in various contexts

No Comments

No Known Activations