INDEX

Explanations

terms indicating inclusion or association with a group

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.09

put

-0.77

me

-0.74

 create

-0.72

get

-0.71

text

-0.71

create

-0.71

/**

-0.71

div

-0.71

 operate

-0.70

POSITIVE LOGITS

 milf

2.10

 increa

2.09

 maneu

2.07

 affor

2.07

 wien

2.04

 🤣🤣

2.03

 stockholm

2.00

 desir

1.99

 inev

1.98

 perfet

1.97

Activations Density 0.053%

terms indicating inclusion or association with a group

No Comments

No Known Activations