INDEX

Explanations

locality, events or actions captured by video recordings

oai_token-act-pair · gpt-3.5-turbo

instances of the word "show" and its variations in the context of videos and visual representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aceutical

-0.83

EEE

-0.75

bury

-0.74

 batted

-0.68

ilings

-0.67

 formulated

-0.66

pton

-0.65

oslav

-0.65

theless

-0.64

 levied

-0.63

POSITIVE LOGITS

 flashes

0.92

 footage

0.89

 clips

0.89

ered

0.89

runners

0.87

 prominently

0.84

 Thumbnails

0.79

 similarities

0.78

 signs

0.76

 photographs

0.75

Activations Density 0.059%

locality, events or actions captured by video recordings

instances of the word "show" and its variations in the context of videos and visual representations

No Comments

No Known Activations