INDEX

Explanations

tools and techniques related to diagnostics and assessment

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ِّف

-0.54

ptid

-0.51

cyklopedia

-0.51

pearance

-0.50

\{\\

-0.50

 crossorigin

-0.48

IllegalArgument

-0.47

ApiProperty

-0.47

wój

-0.47

randa

-0.47

POSITIVE LOGITS

 tools

2.60

 tool

2.44

 Tools

2.20

tools

2.14

tool

2.12

 Tool

2.07

 TOOLS

2.04

Tool

2.02

Tools

2.00

 outils

1.99

Activations Density 0.301%

tools and techniques related to diagnostics and assessment

No Comments

No Known Activations