INDEX

Explanations

numerical ratings presented as fractions or ratios

oai_token-act-pair · gpt-3.5-turbo

ratings and evaluations associated with various items or experiences

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

ilib

-0.72

htaking

-0.68

cedes

-0.66

_-

-0.64

hunt

-0.64

imar

-0.64

 Authorization

-0.63

hai

-0.63

agher

-0.63

lyn

-0.62

POSITIVE LOGITS

 dozen

0.73

 Mbps

0.66

 doors

0.64

onite

0.62

aughtered

0.62

ModLoader

0.60

 thousand

0.59

 Spokane

0.59

 hundred

0.58

Activations Density 0.053%

numerical ratings presented as fractions or ratios

ratings and evaluations associated with various items or experiences

No Comments

No Known Activations