INDEX

Explanations

the word "record" in any context

oai_token-act-pair · gemini-2.0-flash

occurrences of the word "record"

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

record

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 spot

-0.55

UNDA

-0.54

 zvuky

-0.52

Sucesor

-0.52

 MaterialApp

-0.52

 nonatomic

-0.51

 désolés

-0.51

#+#

-0.51

ultad

-0.51

AnchorStyles

-0.51

POSITIVE LOGITS

cshtml

0.54

efficient

0.52

IsMutable

0.50

 vocale

0.50

LookAnd

0.50

copg

0.50

 nakalista

0.49

 ComVisible

0.48

__":

0.48

TintMode

0.48

Activations Density 3.612%

the word "record" in any context

occurrences of the word "record"

record

No Comments

No Known Activations