INDEX

Explanations

statements of 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>

-3.29

ⓧ

-1.07

<?

-0.87

/***

-0.84

/*

-0.83

/**

-0.83

<?

-0.80

/*++

-0.62

//---

-0.61

POSITIVE LOGITS

 statement

1.29

 statements

1.21

statement

1.17

 Statement

1.16

 Statements

1.15

Statements

1.08

Statement

1.07

statements

1.06

 STATEMENT

1.03

STATEMENT

0.96

Activations Density 0.080%

statements of text

No Comments

No Known Activations