INDEX

Explanations

interview

np_max-act-logits · gemini-2.0-flash

words related to conversations

oai_token-act-pair · gemini-2.0-flash

interview

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 interview

-0.72

 Interview

-0.64

 interviewed

-0.63

interview

-0.63

 насељу

-0.62

 interviews

-0.60

colgroup

-0.60

Interview

-0.57

Story

-0.56

Entrevista

-0.54

POSITIVE LOGITS

 Roskov

0.50

omock

0.47

elee

0.47

⋙

0.46

 suspens

0.45

 TURNER

0.45

 VizieR

0.45

 cumin

0.43

 indisponible

0.43

 slab

0.43

Activations Density 1.786%

interview

words related to conversations

interview

No Comments

No Known Activations