INDEX

Explanations

references to libraries and programming constructs in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

+:+

-0.49

קר

-0.47

 valent

-0.46

buster

-0.46

ampu

-0.45

hausen

-0.43

itakan

-0.43

キュ

-0.43

Tikang

-0.43

ISD

-0.42

POSITIVE LOGITS

ConstraintMaker

0.99

OGND

0.97

tagHelperRunner

0.95

 jsPsych

0.90

 dAtA

0.88

fillType

0.87

makeConstraints

0.84

ResumeLayout

0.84

 oprot

0.81

 onOptions

0.79

Activations Density 0.028%

references to libraries and programming constructs in code snippets

No Comments

No Known Activations