INDEX

Explanations

references to healthcare programs and related organizational structures

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

preceding "programme" or "program" (spelled differently)

np_acts-logits-general · gemini-2.0-flash

signalling pathway

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tumors

-1.09

 Tumors

-1.08

 Ее

-1.03

Theater

-0.98

Еще

-0.96

 theaters

-0.94

 theater

-0.93

neighbors

-0.93

 Theater

-0.91

 Theaters

-0.89

POSITIVE LOGITS

şi

1.46

 organisations

1.45

 utilisation

1.43

Ещё

1.42

 unauthorised

1.42

 generalised

1.41

Şi

1.40

Colours

1.40

 organisational

1.39

 fibres

1.37

Activations Density 0.525%

references to healthcare programs and related organizational structures

preceding "programme" or "program" (spelled differently)

signalling pathway

No Comments

No Known Activations