INDEX

Explanations

the prevalence of certain characteristics or phenomena

oai_token-act-pair · gpt-3.5-turbo

terms related to prevalence and incidence statistics

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

ebus

-0.94

zeb

-0.69

asca

-0.67

shaw

-0.66

irlf

-0.66

atom

-0.66

cell

-0.65

imb

-0.64

paio

-0.63

bie

-0.62

POSITIVE LOGITS

 preval

1.19

 prevalence

1.17

 incidence

0.93

rences

0.90

 prevalent

0.82

entimes

0.77

 occurrence

0.76

ãĥ¼ãĥĨãĤ£

0.76

Û

0.74

ality

0.73

Activations Density 0.011%

the prevalence of certain characteristics or phenomena

terms related to prevalence and incidence statistics

No Comments

No Known Activations