INDEX

Explanations

occurrences of the word "strain" and related terms in various scientific contexts

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

strain

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

 المعيارى

-0.91

 EconPapers

-0.86

ⓧ

-0.85

 OMITBAD

-0.80

NewGuid

-0.75

 виправивши

-0.74

 otomatig

-0.71

ymce

-0.70

ThroughAttribute

-0.69

RTEX

-0.69

POSITIVE LOGITS

Strain

1.05

 Strain

1.05

 strain

1.04

strain

0.94

 strains

0.77

 Strains

0.72

 strained

0.61

strains

0.59

strained

0.57

 straining

0.57

Activations Density 0.010%

occurrences of the word "strain" and related terms in various scientific contexts

strain

No Comments

No Known Activations