INDEX

Explanations

elements representing columns in a data structure or layout

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

setupUi

-0.74

IBinder

-0.61

aarrggbb

-0.59

tgz

-0.59

 المعيارى

-0.57

".

-0.57

mergeFrom

-0.54

scriptId

-0.54

principalTable

-0.51

mbggenerated

-0.50

POSITIVE LOGITS

col

2.04

col

1.34

COL

0.96

Col

0.83

colt

0.79

colo

0.79

coll

0.76

IMPORTED

0.74

cols

0.70

 colle

0.69

Activations Density 0.107%

elements representing columns in a data structure or layout

No Comments

No Known Activations