INDEX

Explanations

words related to actions, decisions, and processes

oai_token-act-pair · gpt-3.5-turbo

verbs that indicate actions and processed responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ajo

-0.65

 bush

-0.63

aleb

-0.57

 ethic

-0.56

 gotta

-0.54

dom

-0.54

church

-0.52

mare

-0.52

rament

-0.51

 roots

-0.51

POSITIVE LOGITS

Reply

0.65

 Parenthood

0.62

 Athen

0.61

by

0.61

 ());

0.61

IRED

0.61

 aback

0.61

YING

0.60

quished

0.60

 offline

0.60

Activations Density 0.563%

words related to actions, decisions, and processes

verbs that indicate actions and processed responses

No Comments

No Known Activations