INDEX

Explanations

technical terms and references related to medical and biological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

évaluateur

-0.92

Архівовано

-0.69

üglich

-0.64

حياتها

-0.64

igrette

-0.64

 ExecuteAsync

-0.64

Filmografia

-0.63

 vulgaires

-0.63

ajaja

-0.63

 initComponents

-0.62

POSITIVE LOGITS

DebuggerNonUser

0.69

body

0.60

 body

0.59

 drawer

0.58

 cabinet

0.55

crowd

0.55

coil

0.55

 camper

0.54

 tent

0.53

Zem

0.51

Activations Density 2.629%

technical terms and references related to medical and biological contexts

No Comments

No Known Activations