INDEX

Explanations

code-related terms or commands in a technical context

oai_token-act-pair · gpt-3.5-turbo

specific numerical or statistical terms and references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bilt

-0.73

otine

-0.68

arma

-0.63

fman

-0.63

 compr

-0.63

phia

-0.63

[];

-0.61

alus

-0.61

fir

-0.60

wei

-0.60

POSITIVE LOGITS

 Jinn

0.72

 lett

0.61

HP

0.58

 Voting

0.57

ECK

0.57

 Hague

0.56

ods

0.55

 quotes

0.55

Kee

0.55

Skip

0.54

Activations Density 0.815%

code-related terms or commands in a technical context

specific numerical or statistical terms and references

No Comments

No Known Activations

code-related terms or commands in a technical context

specific numerical or statistical terms and references

No Comments

No Known Activations