INDEX

Explanations

occurrences of identifiers related to IDs in 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 nahilalakip

-0.88

inalg

-0.84

GraphicsUnit

-0.82

monials

-0.80

itemID

-0.72

NOVA

-0.68

ョン

-0.68

 Audiodateien

-0.68

 NOVA

-0.68

 snippetHide

-0.67

POSITIVE LOGITS

Id

2.58

Id

2.05

Ids

1.12

 Idol

0.98

getId

0.97

 Idris

0.96

setId

0.95

 getId

0.95

fileId

0.92

mId

0.91

Activations Density 0.076%

occurrences of identifiers related to IDs in a programming context

No Comments

No Known Activations