INDEX

Explanations

words related to security breaches or either physical or virtual intrusion attempts

oai_token-act-pair · gpt-3.5-turbo

key terms related to security, law enforcement, and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Solitaire

-0.69

 withd

-0.64

etheless

-0.64

 thous

-0.64

rica

-0.63

 Tanz

-0.61

theless

-0.61

aiman

-0.60

ĻĤ

-0.60

 Rampage

-0.59

POSITIVE LOGITS

lessly

1.12

less

1.09

fully

0.84

ively

0.84

ably

0.84

able

0.83

iest

0.82

 guiActiveUn

0.80

LESS

0.78

ally

0.76

Activations Density 0.727%

words related to security breaches or either physical or virtual intrusion attempts

key terms related to security, law enforcement, and societal issues

No Comments

No Known Activations