INDEX

Explanations

phrases indicating involvement in activities or events

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>

-3.14

/**

-0.84

ⓧ

-0.82

/**

-0.68

 himself

-0.65

ОБ

-0.65

 enable

-0.64

 itself

-0.64

太

-0.64

POSITIVE LOGITS

Juf

1.89

 accla

1.83

 reluct

1.72

 disagre

1.71

 Keny

1.69

 wien

1.68

 emphat

1.67

 Intere

1.65

 maneu

1.64

 practition

1.64

Activations Density 0.961%

phrases indicating involvement in activities or events

No Comments

No Known Activations