INDEX

Explanations

words or phrases that are marked by a particular symbol

oai_token-act-pair · gpt-3.5-turbo

references to votes and voting-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hement

-0.71

ings

-0.65

tics

-0.62

cius

-0.62

pace

-0.61

isconsin

-0.58

 Chandler

-0.57

heit

-0.57

uto

-0.57

 Scion

-0.56

POSITIVE LOGITS

?????-

0.72

âĵĺ

0.71

Beta

0.67

ÂłÂłÂłÂł

0.65

ÂłÂłÂł

0.65

inav

0.63

gex

0.63

 +---

0.60

Bonus

0.60

Db

0.60

Activations Density 0.183%

words or phrases that are marked by a particular symbol

references to votes and voting-related terms

No Comments

No Known Activations