INDEX

Explanations

phrases or words related to secrecy or classified information

oai_token-act-pair · gpt-3.5-turbo

references to secrecy and covert operations

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

gaard

-0.85

annis

-0.85

avers

-0.77

gars

-0.73

©¶æ

-0.73

adjusted

-0.72

merce

-0.70

thood

-0.69

chairs

-0.68

older

-0.67

POSITIVE LOGITS

 secret

0.96

ariat

0.95

arial

0.94

rets

0.87

Secret

0.86

 ingredient

0.83

secret

0.81

 ballot

0.79

 secrets

0.78

 unfocusedRange

0.77

Activations Density 0.014%

phrases or words related to secrecy or classified information

references to secrecy and covert operations

No Comments

No Known Activations