INDEX

Explanations

phrases related to positions or rankings in a competitive context

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.05

ⓧ

-0.83

/***

-0.80

/**

-0.76

/*

-0.66

-0.64

Autoritní

-0.62

 introduce

-0.60

Kontrola

-0.59

Хро

-0.59

POSITIVE LOGITS

 stockholm

1.65

 Minang

1.64

 maneu

1.61

 affor

1.57

 disagre

1.55

 lidl

1.54

 emphat

1.53

 impra

1.51

Juf

1.50

 accla

1.50

Activations Density 0.091%

phrases related to positions or rankings in a competitive context

No Comments

No Known Activations