INDEX

Explanations

blocks of code or documentation comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Rolf

-0.96

<()>

-0.96

RegressionTest

-0.86

 NgModule

-0.82

 CreateTagHelper

-0.81

’”

-0.81

nodoc

-0.80

 Rolf

-0.80

Vos

-0.79

windowFixed

-0.77

POSITIVE LOGITS

1.30

1.14

1.10

</i>

0.91

0.90

0.89

iarkan

0.89

0.87

</b>

0.82

Activations Density 0.228%

blocks of code or documentation comments

No Comments

No Known Activations