INDEX

Explanations

terms related to the film industry, particularly focusing on aspects related to movies and cinematic motion

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "motion" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

rosso

-0.73

ãĤ¨ãĥ«

-0.66

iders

-0.66

scl

-0.65

 Chap

-0.64

dds

-0.64

 Province

-0.64

iott

-0.62

inia

-0.62

MJ

-0.61

POSITIVE LOGITS

 motion

0.94

 blur

0.90

 Picture

0.88

 sickness

0.87

 Motion

0.86

Motion

0.85

picture

0.84

motion

0.83

immune

0.81

 motions

0.77

Activations Density 0.035%

terms related to the film industry, particularly focusing on aspects related to movies and cinematic motion

occurrences of the word "motion" and its variations

No Comments

No Known Activations