INDEX

Explanations

names or words related to actions of awakening

oai_token-act-pair · gpt-3.5-turbo

words related to mistakes and errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

heter

-0.71

mson

-0.69

brates

-0.63

actionDate

-0.62

posium

-0.62

rolog

-0.61

brate

-0.60

 includ

-0.60

 thor

-0.60

acious

-0.59

POSITIVE LOGITS

aken

0.87

iak

0.83

fold

0.80

alia

0.80

umber

0.80

ede

0.77

ication

0.74

unciation

0.72

atche

0.72

nered

0.72

Activations Density 0.015%

names or words related to actions of awakening

words related to mistakes and errors

No Comments

No Known Activations