INDEX

Explanations

detailed analysis and examinations of various subjects or fields

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>

-3.15

/***

-0.74

ⓧ

-0.73

-0.68

/*!

-0.63

 patted

-0.56

/*++

-0.55

<?

-0.55

 knelt

-0.55

 petitioned

-0.55

POSITIVE LOGITS

 analysis

1.09

 maneu

1.04

analysis

1.03

 Analysis

1.01

 analy

1.00

 analys

0.98

 analyses

0.98

 soggior

0.97

 analisi

0.96

 wald

0.94

Activations Density 0.094%

detailed analysis and examinations of various subjects or fields

No Comments

No Known Activations