INDEX

Explanations

phrases related to experience measured in years

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

years of experience

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

("")]

-0.39

🔀

-0.38

IsPostBack

-0.38

حوالہ

-0.38

 AssemblyCulture

-0.36

 controlado

-0.36

AutoScaleMode

-0.35

 thereupon

-0.35

 PARTIES

-0.35

сылкі

-0.35

POSITIVE LOGITS

rawDesc

0.54

RTEX

0.50

 continuous

0.49

been

0.47

PYX

0.47

Kip

0.47

entet

0.46

ませ

0.45

cellent

0.45

 Been

0.45

Activations Density 0.005%

phrases related to experience measured in years

years of experience

No Comments

No Known Activations