INDEX

Explanations

code-related terminology and structures within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

CodeAttribute

-0.67

 SDLK

-0.58

tabak

-0.52

 Buxton

-0.52

Identyfik

-0.51

imei

-0.50

acterium

-0.50

 Guil

-0.49

 Kwang

-0.49

Facial

-0.49

POSITIVE LOGITS

 adapter

1.14

 Adapter

1.12

ViewHolder

1.09

Adapter

1.07

adapter

0.99

 ViewHolder

0.96

DataAdapter

0.91

 adapters

0.90

 Adap

0.87

BaseAdapter

0.87

Activations Density 0.112%

code-related terminology and structures within a programming context

No Comments

No Known Activations