INDEX

Explanations

references to actions or states related to legal proceedings and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

)"),

-0.65

'])->

-0.60

RegressionTest

-0.57

)))));

-0.57

 ***!

-0.57

aarrggbb

-0.56

:+:

-0.56

 invokingState

-0.53

AxisAlignment

-0.53

)))),

-0.52

POSITIVE LOGITS

 dedans

0.69

uxxxx

0.68



0.67

 ziua

0.66

 للمعارف

0.63

 vendus

0.58

حياته

0.57

 diritti

0.56

labus

0.55

 foncé

0.55

Activations Density 0.480%

references to actions or states related to legal proceedings and consequences

No Comments

No Known Activations