INDEX

Explanations

technical terms and elements related to data structures and programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.58

—

-0.56

EDEFAULT

-0.56

,"

-0.54

—

-0.53

-0.50

dawnictwo

-0.49

-0.48

POSITIVE LOGITS

Efq

0.86

neſs

0.84

 themſelves

0.79

 pleaſure

0.76

 snippetHide

0.75

 Reſ

0.75

 ſtate

0.75

 Monfieur

0.74

 Houſe

0.73

 myſelf

0.73

Activations Density 0.327%

technical terms and elements related to data structures and programming syntax

No Comments

No Known Activations