INDEX

Explanations

references to groups of people involved in significant events or discussions

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>

-2.40

 solidar

-1.02

 dras

-1.00

/***

-0.92

 utop

-0.89

 geograf

-0.87

/**

-0.87

 ideolog

-0.84

 abstra

-0.83

 impon

-0.82

POSITIVE LOGITS

 unspeak

1.11

 disreg

1.10

 unwarran

1.08

 impractica

1.05

 unlaw

1.05

 indestru

1.05

 caucasian

1.00

 cuck

1.00

 ingrat

0.97

 pamph

0.97

Activations Density 0.439%

references to groups of people involved in significant events or discussions

No Comments

No Known Activations