INDEX

Explanations

code snippets or programming-related content

oai_token-act-pair · gemini-2.0-flash

programming elements or code structures

np_token-act-pair-logits · gpt-4o-mini

<

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<unused63>

-0.47

<unused61>

-0.46

gnition

-0.43

handleRequest

-0.43

</h1>

-0.42

 tunnels

-0.42

-0.41

 crotch

-0.41

byg

-0.41

<unused60>

-0.41

POSITIVE LOGITS

MLLoader

1.04

 متعلقه

0.79

цездатний

0.77

aarrggbb

0.77

 ModelExpression

0.77

 estimés

0.77

abestanden

0.76

 חיצוניים

0.74

 zelve

0.74

 GenerationType

0.72

Activations Density 3.022%

code snippets or programming-related content

programming elements or code structures

<

No Comments

No Known Activations