INDEX

Explanations

programming-related syntax and structure

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

 jsPsych

-0.91

tvguidetime

-0.77

ropractic

-0.68

Efq

-0.68

locene

-0.65

OrBuilder

-0.64

fjspx

-0.64

AndEndTag

-0.62

Hozzáférés

-0.62

 Daß

-0.61

POSITIVE LOGITS

((

0.61

ResumeLayout

0.55

 surla

0.54

((

0.53

this

0.52

BASELINE

0.51

či

0.49

 дописавши

0.47

ur

0.46

ir

0.46

Activations Density 0.014%

programming-related syntax and structure

No Comments

No Known Activations