INDEX

Explanations

programming-related syntax and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ſeveral

-0.84

 pleaſure

-0.71

 itſelf

-0.68

 iſt

-0.67

 himſelf

-0.66

 ***!

-0.65

 themſelves

-0.63

 purpoſe

-0.62

 juſ

-0.61

 unſ

-0.59

POSITIVE LOGITS

package

1.21

//

0.98

import

0.87

0.79

/*

0.66

 createSlice

0.64

DOCTYPE

0.63

IContainer

0.62

/**

0.61

,:),

0.60

Activations Density 0.067%

programming-related syntax and structures

No Comments

No Known Activations