INDEX

Explanations

mentions of specific names or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names related to specific individuals or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

urrent

-0.77

ourse

-0.76

theless

-0.74

activated

-0.73

cision

-0.72

ortium

-0.72

xual

-0.72

cember

-0.72

grading

-0.71

grades

-0.71

POSITIVE LOGITS

glers

1.11

Gw

0.86

Gad

0.86

aciously

0.84

acity

0.80

ILA

0.76

sonian

0.74

mong

0.72

 Hick

0.71

aneers

0.70

Activations Density 0.029%

mentions of specific names or locations

proper nouns and names related to specific individuals or locations

No Comments

No Known Activations