INDEX

Explanations

code-related keywords and structure in programming documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 oprot

-1.05

IsMutable

-1.01

principalColumn

-0.97

 betweenstory

-0.89

featureID

-0.88

 protoimpl

-0.87

 AttributeSet

-0.85

CWE

-0.85

 StringTokenizer

-0.82

setVerticalGroup

-0.81

POSITIVE LOGITS

import

1.86

 import

1.17

 Import

0.93

Import

0.84

 importing

0.76

 importa

0.74

 IMPORT

0.69

 imported

0.67

Importing

0.65

'./

0.65

Activations Density 0.009%

code-related keywords and structure in programming documentation

No Comments

No Known Activations