INDEX

Explanations

technical terms related to software analysis and programming

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shenan

-1.40

 impra

-1.39

 maneu

-1.33

 reluct

-1.32

 encomp

-1.32

 unve

-1.32

 depic

-1.29

 increa

-1.29

 disagre

-1.26

 reconno

-1.25

POSITIVE LOGITS

 static

1.18

static

1.15

Static

1.09

STATIC

1.04

 Static

0.99

isStatic

0.89

静态

0.79

静

0.74

statics

0.71

 fixed

0.71

Activations Density 0.135%

technical terms related to software analysis and programming

No Comments

No Known Activations