INDEX

Explanations

locations and names, especially those related to legal or medical contexts

oai_token-act-pair · gpt-3.5-turbo

references to specific locations and individuals, particularly names

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

smoking

-0.73

aceous

-0.71

ILE

-0.69

=-=-=-=-=-=-=-=-

-0.68

TPP

-0.68

eger

-0.67

uality

-0.66

apers

-0.65

Japanese

-0.64

zza

-0.64

POSITIVE LOGITS

 Nass

1.16

daq

1.03

essor

0.85

mares

0.81

itud

0.78

 Tanz

0.75

aran

0.74

itude

0.72

arus

0.71

 horizont

0.71

Activations Density 0.005%

locations and names, especially those related to legal or medical contexts

references to specific locations and individuals, particularly names

No Comments

No Known Activations