INDEX

Explanations

terms related to anti-drug or therapeutic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Numerology

-0.92

URLException

-0.90

OGND

-0.87

 beginnetje

-0.86

zzlies

-0.81

 magasiner

-0.78

LabelTagHelper

-0.78

httphttps

-0.77

')"

-0.77

']")

-0.76

POSITIVE LOGITS

 anti

2.21

 Anti

2.17

Anti

2.09

 ANTI

1.92

anti

1.91

ANTI

1.66

 antis

1.60

 antig

1.57

 Анти

1.57

 анти

1.47

Activations Density 0.065%

terms related to anti-drug or therapeutic concepts

No Comments

No Known Activations