INDEX

Explanations

programming-related attributes and identifiers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

JNIEnv

-0.84

localctx

-0.79

UIControlState

-0.77

mongoose

-0.74

 ContentValues

-0.73

ContentValues

-0.72

 propOrder

-0.70

 CURLOPT

-0.70

ContentLoaded

-0.68

PyObject

-0.67

POSITIVE LOGITS

Guid

0.75

 ResponseEntity

0.74

 UUID

0.74

UUID

0.73

 useEffect

0.72

useEffect

0.71

 ComVisible

0.69

uuid

0.68

IBOutlet

0.68

guid

0.65

Activations Density 0.011%

programming-related attributes and identifiers

No Comments

No Known Activations