INDEX

Explanations

the word "one"

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>

-2.78

<?

-1.04

-0.91

/***

-0.88

/**

-0.77

ⓧ

-0.73

/*

-0.72

 intersper

-0.70

 reunite

-0.70

<?

-0.70

POSITIVE LOGITS

 eduardo

0.84

 sovere

0.79

 sappi

0.79

 Minang

0.79

 vectra

0.79

 sergio

0.78

 tucson

0.77

 chrysler

0.77

 bandung

0.77

 rodrigo

0.77

Activations Density 0.149%

the word "one"

No Comments

No Known Activations