INDEX

Explanations

specific parts or components specified in a text

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>

-3.17

/***

-0.81

 eliminate

-0.66

/*!

-0.65

<?

-0.63

///**

-0.63

/*

-0.63

 consolidate

-0.61

ⓧ

-0.60

POSITIVE LOGITS

 stockholm

1.14

 lidl

1.10

mef

1.10

aen

1.09

 Parts

1.04

 prétend

1.03

 maroc

1.03

 wien

1.03

 lele

1.02

 catég

1.02

Activations Density 0.122%

specific parts or components specified in a text

No Comments

No Known Activations