INDEX

Explanations

locations and statistical information

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in" indicating various contexts or categories

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

soever

-0.97

past

-0.66

 thou

-0.65

bass

-0.65

rang

-0.65

ï¸ı

-0.65

ens

-0.64

River

-0.63

pill

-0.63

 flaw

-0.63

POSITIVE LOGITS

 terms

1.23

 regards

1.13

 regard

1.07

ventory

0.88

roads

0.87

 spite

0.87

 vitro

0.86

 favor

0.85

clus

0.84

 attendance

0.84

Activations Density 0.231%

locations and statistical information

instances of the word "in" indicating various contexts or categories

No Comments

No Known Activations