INDEX

Explanations

phrases and contexts that suggest openness or receptiveness to ideas and evidence

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>

-3.28

SequentialGroup

-0.74

toBeDefined

-0.74

getClassLoader

-0.71

<?

-0.71

/**

-0.69

/***/

-0.68

run

-0.65

cout

-0.65

 also

-0.64

POSITIVE LOGITS

 maneu

1.93

 stockholm

1.81

hcm

1.81

 impra

1.80

 affor

1.78

 increa

1.77

 accla

1.75

Juf

1.75

 reluct

1.74

 roberto

1.72

Activations Density 0.417%

phrases and contexts that suggest openness or receptiveness to ideas and evidence

No Comments

No Known Activations