INDEX

Explanations

references to parameters in programming or data queries

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

code parameters

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

objs

-0.43

angdong

-0.42

hObject

-0.40

 Abstr

-0.39

Sup

-0.39

Fract

-0.37

Libs

-0.37

Cro

-0.36

Bru

-0.36

fclose

-0.36

POSITIVE LOGITS

Parameters

2.80

 Parameters

1.72

PARAMETERS

1.45

getParameters

1.40

parameters

1.35

 PARAMETERS

1.19

 parameters

1.08

Parameter

0.97

 Parameter

0.94

 PARAMETER

0.83

Activations Density 0.003%

references to parameters in programming or data queries

code parameters

No Comments

No Known Activations

references to parameters in programming or data queries

code parameters

No Comments

No Known Activations