INDEX

Explanations

terms related to aggressive language and references to women, particularly in roles related to acting or performance

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>

-1.61

ⓧ

-0.81

AnchorTagHelper

-0.76

IonicModule

-0.75

Itoa

-0.69

//}

-0.69

maxcdn

-0.69

rungsseite

-0.66

 المعرف

-0.66

Viungo

-0.65

POSITIVE LOGITS

Juf

1.33

 maneu

1.24

 gaily

1.21

 disagre

1.19

 beaute

1.17

 stockholm

1.14

 withal

1.10

 unspeak

1.09

 tolerably

1.08

 squa

1.07

Activations Density 0.194%

terms related to aggressive language and references to women, particularly in roles related to acting or performance

No Comments

No Known Activations