INDEX

Explanations

instances of specific formatting or punctuation in text

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

`<start_of_turn>user`

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

etCode

-0.44

TableAdapter

-0.41

DebuggerNonUser

-0.35

BeginContext

-0.35

 bicarbon

-0.35

 transfieras

-0.35

 Spri

-0.35

copg

-0.34

теризу

-0.34

windowFixed

-0.34

POSITIVE LOGITS

 détaillée

0.82



0.68

Carriera

0.63

 propOrder

0.59

новништво

0.50

ooc

0.50

ElementException

0.49

躇

0.49

ruptedException

0.48

 wireType

0.48

Activations Density 0.000%

instances of specific formatting or punctuation in text

`<start_of_turn>user`

No Comments

No Known Activations

instances of specific formatting or punctuation in text

`<start_of_turn>user`

No Comments

No Known Activations