INDEX

Explanations

clips or segments within a larger piece of media

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 @ 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

ichick

-0.94

iott

-0.93

velt

-0.86

ccording

-0.79

ksh

-0.73

chwitz

-0.70

abad

-0.70

ignt

-0.69

ADRA

-0.68

 Schwarz

-0.67

POSITIVE LOGITS

 clips

1.09

 clip

1.03

clips

1.01

clip

0.94

 footage

0.88

 Clip

0.86

boards

0.84

scenes

0.83

utic

0.80

ograp

0.80

Activations Density 0.027%

clips or segments within a larger piece of media

references to video clips

No Comments

No Known Activations