INDEX

Explanations

references to specific identifiers or values within a structured data format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ContentAsync

-0.73

 snippetHide

-0.71

 &___

-0.68

—

-0.65

%");

-0.64

 doInBackground

-0.62

 Kearney

-0.62

 henvisninger

-0.62

herself

-0.61

abestanden

-0.60

POSITIVE LOGITS

ABC

0.61

ABCDEF

0.61

 ABCD

0.60

qwerty

0.59

abc

0.59

ABCD

0.58

ABC

0.54

abc

0.54

abcdef

0.51

SDF

0.50

Activations Density 0.392%

references to specific identifiers or values within a structured data format

No Comments

No Known Activations