INDEX

Explanations

the word "and."

oai_token-act-pair · gemini-2.0-flash

occurrences of the word "and"

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

and

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

plaatsen

-0.55

考え

-0.52

考えて

-0.49

jublj

-0.48

ânica

-0.46

KEYCODE

-0.46

kháu

-0.45

 volant

-0.44

[:]

-0.44

Rüyada

-0.44

POSITIVE LOGITS

مصادر

0.68

`{.

0.59

ArgsConstructor

0.58

EndContext

0.58

 يتيمه

0.57

AccessorTable

0.57

alors

0.55

tonode

0.55

日閲覧

0.54

gt

0.54

Activations Density 0.858%

the word "and."

occurrences of the word "and"

and

No Comments

No Known Activations