INDEX

Explanations

lines of code or commands within a programming or scripting context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-1.03

 autorytatywna

-0.93

 Signalez

-0.89

LookAnd

-0.86

mybatisplus

-0.85

 Савезне

-0.84

SerializedSize

-0.82

 oprot

-0.81

IndentedString

-0.81

Tembelea

-0.81

POSITIVE LOGITS

↵↵

1.09

<eos>

0.90

↵

0.70

<h2>

0.64

↵↵↵

0.59

0.58

↵↵↵↵↵

0.57

↵↵↵↵↵↵

0.57

↵↵↵↵

0.54

setVerticalGroup

0.49

Activations Density 0.106%

lines of code or commands within a programming or scripting context

No Comments

No Known Activations