INDEX

Explanations

references to data input specifications

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>

-3.05

/*

-0.92

/***

-0.91

/**

-0.89

<?

-0.86

-0.80

<?

-0.78

ⓧ

-0.68

 ratify

-0.66

 localize

-0.65

POSITIVE LOGITS

 input

1.12

 Input

1.11

 Inputs

1.10

 inputs

1.06

 INPUT

1.04

input

1.03

 silikon

1.03

Input

1.02

inputData

1.01

 keramik

0.99

Activations Density 0.050%

references to data input specifications

No Comments

No Known Activations