INDEX

Explanations

sentiment about movies and books, especially discussing flaws or mixed feelings.

oai_token-act-pair · gemini-2.0-flash

complex or advanced terminology

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

negative reviews

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

 myſelf

-0.69

 MainAxisSize

-0.68

UrlResolution

-0.63

AsUp

-0.63

tvguidetime

-0.62

축

-0.59

 חיצוניים

-0.59

 scoperto

-0.59

'];

-0.59

']))

-0.59

POSITIVE LOGITS

enschappelijke

0.59

 Vikipedi

0.46

hObject

0.46

 MyBatis

0.45

lccn

0.44

im

0.42

assume

0.42

amse

0.42

 Tele

0.42

 rushed

0.41

Activations Density 1.964%

sentiment about movies and books, especially discussing flaws or mixed feelings.

complex or advanced terminology

negative reviews

No Comments

No Known Activations