INDEX

Explanations

words related to technology and materials

oai_token-act-pair · gpt-3.5-turbo

references to items or themes associated with the term "meta."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 innocence

-0.69

 Mahjong

-0.68

SPONSORED

-0.63

heit

-0.62

*/(

-0.61

 peek

-0.60

hood

-0.59

ongyang

-0.58

Fa

-0.58

 imitation

-0.58

POSITIVE LOGITS

ritic

0.99

urgy

0.88

roth

0.83

ritical

0.76

henko

0.75

rites

0.74

roy

0.73

uries

0.73

ocr

0.72

opolis

0.71

Activations Density 0.113%

words related to technology and materials

references to items or themes associated with the term "meta."

No Comments

No Known Activations