INDEX

Explanations

occurrences of import statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

principalColumn

-0.99

ThroughAttribute

-0.89

featureID

-0.87

CWE

-0.85

 useStyles

-0.81

 oprot

-0.79

IsMutable

-0.77

unhofer

-0.75

WriteTagHelper

-0.75

RenderAtEndOf

-0.74

POSITIVE LOGITS

import

2.02

 import

1.07

 Import

0.74

Import

0.70

 importing

0.64

 IMPORT

0.62

 importa

0.61

 Schicht

0.59

 imports

0.57

 Buxton

0.57

Activations Density 0.008%

occurrences of import statements in code

No Comments

No Known Activations