INDEX

Explanations

references to behavioral patterns and changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Laurens

-0.82

 Milne

-0.76

 Donne

-0.75

Nip

-0.73

 fairest

-0.71

 Frye

-0.69

 geschlagen

-0.69

 skar

-0.69

 glomer

-0.69

 aquifers

-0.68

POSITIVE LOGITS

 behavior

1.73

 behaviour

1.68

 behaviors

1.50

 Behavior

1.50

 behaviours

1.47

behavior

1.46

 Behaviour

1.41

behaviour

1.40

 BEHAVIOR

1.40

Behavior

1.36

Activations Density 0.110%

references to behavioral patterns and changes

No Comments

No Known Activations