INDEX

Explanations

symbols or annotations indicating data points or references

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

 NgModule

-0.79

NamedQueries

-0.70

setopt

-0.70

GeoNames

-0.69

asanjo

-0.67

 SafeMath

-0.64

TestTools

-0.62

::{

-0.62

InjectAttribute

-0.62

sidemargin

-0.61

POSITIVE LOGITS

 collapse

1.10

collapse

1.05

 collapses

0.99

 collapsing

0.95

 Collapse

0.89

 collapsed

0.77

Collapse

0.65

-->

0.64

collapsed

0.62

 basili

0.59

Activations Density 0.065%

symbols or annotations indicating data points or references

No Comments

No Known Activations