INDEX

Explanations

phrases related to locations or places

oai_token-act-pair · gpt-3.5-turbo

the end of a document or a section break

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

Intern

-0.65

ãĥ¼ãĥĨ

-0.62

 destro

-0.60

chuk

-0.59

{{

-0.58

 Nemesis

-0.57

 Horizon

-0.57

 Mour

-0.57

Knight

-0.56

Eth

-0.56

POSITIVE LOGITS

 largeDownload

0.68

bra

0.65

actionDate

0.61

ye

0.61

netflix

0.60

rw

0.60

othe

0.58

wolf

0.57

cause

0.56

hit

0.55

Activations Density 0.254%

phrases related to locations or places

the end of a document or a section break

No Comments

No Known Activations