INDEX

Explanations

elements related to programs or initiatives

oai_token-act-pair · gpt-3.5-turbo

mentions of specific programs or initiatives

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stake

-0.72

vg

-0.69

AAAA

-0.69

thal

-0.68

pg

-0.67

 treacherous

-0.67

 vapor

-0.61

structed

-0.61

usalem

-0.60

 Chic

-0.59

POSITIVE LOGITS

 programme

1.30

 programmes

1.26

 Programme

1.22

mable

0.89

eers

0.82

ĸļ

0.81

oleon

0.81

 programs

0.79

 program

0.78

eering

0.77

Activations Density 0.009%

elements related to programs or initiatives

mentions of specific programs or initiatives

No Comments

No Known Activations