INDEX

Explanations

phrases indicating specific areas or contexts within a larger discussion

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

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

-0.47

 aspects

-0.45

-0.43

 asas

-0.40

-0.39

 nivelul

-0.38

BaseType

-0.38

POSITIVE LOGITS

 activity

0.91

 inspiration

0.88

 creativity

0.86

AnchorStyles

0.84

TemporalType

0.82

insatz

0.80

 experimentation

0.79

 influence

0.78

 activism

0.78

:✨

0.77

Activations Density 0.560%

phrases indicating specific areas or contexts within a larger discussion

No Comments

No Known Activations