INDEX

Explanations

terminology related to testing and evaluation processes in computing

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

 getRule

-0.78

 BIBSYS

-0.74

setopt

-0.73

InstanceState

-0.73

 VIAF

-0.71

rrggbb

-0.69

Ruh

-0.64

hommes

-0.63

égard

-0.61

Koordinaten

-0.60

POSITIVE LOGITS

gggg

1.10

tons

0.99

redients

0.89

GGGG

0.87

ggg

0.86

ging

0.82

ly

0.81

DebuggerNonUser

0.81

redient

0.76

LY

0.73

Activations Density 0.870%

terminology related to testing and evaluation processes in computing

No Comments

No Known Activations