INDEX

Explanations

phrases related to activities and entertainment, such as gaming, racing, thrilling car stunts, and cinematic experiences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.54

}{||

-0.80

glBind

-0.80

<?

-0.76

/*++

-0.76

ⓧ

-0.76

/*

-0.74

/**

-0.73

HasAnnotation

-0.70

lateinit

-0.70

POSITIVE LOGITS

 unden

1.96

 impra

1.90

 affor

1.88

 oleo

1.82

 increa

1.77

 emphat

1.74

 scrat

1.72

 fluo

1.71

 maneu

1.71

 stockholm

1.70

Activations Density 0.842%

phrases related to activities and entertainment, such as gaming, racing, thrilling car stunts, and cinematic experiences

No Comments

No Known Activations