INDEX

Explanations

references to violent actions or crimes involving physical harm to individuals

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Sqft

-0.70

 meras

-0.69

 kemer

-0.66

AnchorStyles

-0.64

bitat

-0.62

 ekos

-0.61

postIndex

-0.60

 plis

-0.59

 quí

-0.59

\{\\

-0.58

POSITIVE LOGITS

 carrefour

0.83

 désert

0.83

 suivie

0.81

 jurassic

0.78

 joyeux

0.77

 fameux

0.77

 mystère

0.75

Yeet

0.75

Wtf

0.74

 triomphe

0.74

Activations Density 0.183%

references to violent actions or crimes involving physical harm to individuals

No Comments

No Known Activations