INDEX

Explanations

terms related to outcomes or results in various contexts

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

"result" or "results" followed by "in" or "ing"

np_acts-logits-general · gemini-2.0-flash

result in

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ialmente

-0.67

Rohy

-0.61

اطر

-0.51

fice

-0.49

зня

-0.48

viously

-0.48

contentPadding

-0.47

 onlyOwner

-0.47

ogens

-0.46

addContainerGap

-0.46

POSITIVE LOGITS

स्व

0.67

물

0.64

Quo

0.62

المكان

0.62

出版年

0.61

PYX

0.61

RCS

0.59

 oriented

0.58

Orient

0.55

 getResult

0.55

Activations Density 0.192%

terms related to outcomes or results in various contexts

"result" or "results" followed by "in" or "ing"

result in

No Comments

No Known Activations