INDEX

Explanations

numerical values

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character or symbol

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

chnology

-0.89

 explan

-0.76

 horizont

-0.75

 agre

-0.74

 incorpor

-0.72

ngth

-0.72

 masse

-0.71

 viability

-0.71

 distingu

-0.71

 manif

-0.69

POSITIVE LOGITS

é¾į

0.95

ļ

0.91

Ĺ

0.88

Ĭ

0.86

¤

0.84

Â°

0.84

º

0.83

Âº

0.83

ef

0.83

Ī

0.82

Activations Density 0.067%

numerical values

occurrences of a specific character or symbol

No Comments

No Known Activations