INDEX

Explanations

references to investigations or inquiries into actions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ArgsConstructor

-0.59

setof

-0.55

EndContext

-0.55

EditorBrowsable

-0.55

SOUNDBITE

-0.55

StructEnd

-0.54

iestety

-0.54

null

-0.53

upakan

-0.52

èvre

-0.52

POSITIVE LOGITS

 other

1.00

 besides

0.92

 beyond

0.88

 unrelated

0.87

 regardless

0.83

不止

0.81

 independent

0.81

non

0.80

 autres

0.79

 outras

0.79

Activations Density 0.698%

references to investigations or inquiries into actions and their consequences

No Comments

No Known Activations