INDEX

Explanations

mathematical limits and properties related to their evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ječ

-0.52

ündete

-0.50

ompi

-0.50

वार

-0.48

 Nakamura

-0.48

Rough

-0.47

疱

-0.47

dbury

-0.47

 kari

-0.46

AccessorTable

-0.46

POSITIVE LOGITS

thâu

0.73

rrggbb

0.71

bootstrapcdn

0.69

CWE

0.69

 ModelExpression

0.67

 transfieras

0.65

Convergence

0.65

convergence

0.64

ímite

0.64

ValueStyle

0.63

Activations Density 0.638%

mathematical limits and properties related to their evaluation

No Comments

No Known Activations