INDEX

Explanations

numbers or values related to statistics, ratings, or measurements

oai_token-act-pair · gpt-3.5-turbo

phrases indicating statistical values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Registered

-0.82

Tact

-0.71

SPONSORED

-0.69

Words

-0.69

hester

-0.68

GROUP

-0.65

Reply

-0.65

atto

-0.64

Comments

-0.64

Whe

-0.63

POSITIVE LOGITS

 least

1.17

onement

1.01

olls

0.84

 approximately

0.83

0.81

 infinity

0.79

roph

0.79

 around

0.79

 Â¥

0.78

 stake

0.77

Activations Density 0.073%

numbers or values related to statistics, ratings, or measurements

phrases indicating statistical values or measurements

No Comments

No Known Activations