INDEX

Explanations

references to political decisions and candidate dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

なども

-0.64

 hẳn

-0.64

などは

-0.61

 chiar

-0.60

 محفوظة

-0.60

oredCriteria

-0.59

 zelfs

-0.59

 كومونز

-0.58

 ویکی‌پدیا

-0.58

 など

-0.58

POSITIVE LOGITS

 damn

1.01

 dammit

0.99

 goddamn

0.97

 fucking

0.94

 damned

0.91

 DAMN

0.85

damn

0.81

fucking

0.79

 freakin

0.78

 fuckin

0.78

Activations Density 0.502%

references to political decisions and candidate dynamics

No Comments

No Known Activations