INDEX

Explanations

references to personal experiences and preferences

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

 assumption

-0.52

dne

-0.50

assumption

-0.47

veden

-0.47

)](

-0.47

 doty

-0.46

 lesz

-0.46

 prés

-0.45

DataAnnotations

-0.44

proven

-0.44

POSITIVE LOGITS

 regularly

1.59

 frequently

1.51

 routinely

1.50

 often

1.45

 occasionally

1.44

 always

1.36

 rarely

1.32

 sometimes

1.32

 usually

1.28

frequently

1.24

Activations Density 0.556%

references to personal experiences and preferences

No Comments

No Known Activations