INDEX

Explanations

occurrences of the word "look" followed by a number or a specific phrase structure indicating a comparison

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>

-2.64

<?

-1.15

ⓧ

-0.95

-0.94

/**

-0.92

<?

-0.90

/*

-0.86

/***

-0.68

lateinit

-0.65

pub

-0.59

POSITIVE LOGITS

 maneu

1.65

 affor

1.60

 shenan

1.54

 accla

1.52

 impra

1.50

 disreg

1.47

 increa

1.42

 unspeak

1.42

 disagre

1.41

 inev

1.38

Activations Density 0.603%

occurrences of the word "look" followed by a number or a specific phrase structure indicating a comparison

No Comments

No Known Activations