INDEX

Explanations

numbers and percentages

oai_token-act-pair · gpt-3.5-turbo

metrics and trends related to numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Magikarp

-0.63

SPONSORED

-0.60

ITNESS

-0.59

Ã®

-0.55

£ı

-0.55

assadors

-0.55

ensitivity

-0.55

encers

-0.54

encer

-0.53

iott

-0.52

POSITIVE LOGITS

 seams

0.86

cember

0.76

ecause

0.72

lins

0.69

 heels

0.66

 throats

0.66

_>

0.66

ilogy

0.62

hed

0.59

 prematurely

0.58

Activations Density 1.190%

numbers and percentages

metrics and trends related to numerical data

No Comments

No Known Activations