INDEX

Explanations

sequences of whitespace or formatting patterns

oai_token-act-pair · gpt-4o-mini Triggered by @bot

programming code keywords

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

keyColumn

-0.38

fromnode

-0.38

WriteBarrier

-0.36

 trône

-0.35

Predecesor

-0.34

 (‘

-0.33

 accion

-0.33

 (“

-0.32

ExecuteReader

-0.32

 („

-0.32

POSITIVE LOGITS

 NgModule

0.59

tanleria

0.57

########.

0.55

usepackage

0.52

DebuggerNonUser

0.51

nodoc

0.50

||=

0.50

tagPool

0.50

Portail

0.49

 sockaddr

0.49

Activations Density 0.002%

sequences of whitespace or formatting patterns

programming code keywords

No Comments

No Known Activations