INDEX

Explanations

mentions of video or film clips

oai_token-act-pair · gpt-3.5-turbo

references to video clips

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

iott

-0.89

ichick

-0.68

ADRA

-0.67

ebus

-0.67

 Schwarz

-0.66

Magikarp

-0.66

 hemor

-0.65

pta

-0.63

 settlement

-0.62

forces

-0.61

POSITIVE LOGITS

 clips

1.26

 clip

1.19

clips

1.10

 footage

1.08

clip

1.04

 uploaded

0.98

 filmed

0.97

 Clip

0.95

scenes

0.95

 snippets

0.94

Activations Density 0.053%

mentions of video or film clips

references to video clips

No Comments

No Known Activations