INDEX

Explanations

references to individuals perceived as suspects in criminal contexts

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.10

/*!

-0.85

lateinit

-0.84

ⓧ

-0.74

displayquote

-0.74

/***

-0.68

glBegin

-0.67

define

-0.66

<?

-0.66

private

-0.66

POSITIVE LOGITS

 thut

1.92

fta

1.79

aen

1.71

 wien

1.66

 stockholm

1.65

 squa

1.65

ftu

1.62

tew

1.62

 fays

1.56

fup

1.54

Activations Density 0.038%

references to individuals perceived as suspects in criminal contexts

No Comments

No Known Activations