INDEX

Explanations

mentions of the letter 's'

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>

-2.81

/**

-0.90

/*

-0.80

<?

-0.72

StringCopy

-0.66

-0.65

/***

-0.64

HasIndex

-0.64

 муніципалі

-0.64

lateinit

-0.64

POSITIVE LOGITS

 affor

1.82

Juf

1.72

 unlaw

1.65

 increa

1.64

 sovere

1.60

 accla

1.60

 emphat

1.53

 impractica

1.52

 milf

1.51

 inev

1.51

Activations Density 0.195%

mentions of the letter 's'

No Comments

No Known Activations