INDEX

Explanations

terms related to brain anatomy and function, especially in memory and visual processing

oai_token-act-pair · gemini-2.0-flash

references to specific terms or objects in research

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

brain functions

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

transQ

-0.66

 '\\;'

-0.62

 psychos

-0.60

invokeLater

-0.60

 consciousness

-0.58

 MainAxisSize

-0.56

WithTag

-0.56

ibatis

-0.56

psycho

-0.56

 subconscious

-0.55

POSITIVE LOGITS

 getItemId

0.56

الحياه

0.56

 متعلقه

0.54

참고

0.54

//

0.53

ylvan

0.51

izer

0.49

Counter

0.47

 counter

0.45

PropertyGroup

0.45

Activations Density 2.393%

terms related to brain anatomy and function, especially in memory and visual processing

references to specific terms or objects in research

brain functions

No Comments

No Known Activations