INDEX

Explanations

references to specific examples or clarifications within a discussion

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

)|^{

-0.53

GEBURTS

-0.53

IntoConstraints

-0.52

Fprintf

-0.51

ñores

-0.47

stolen

-0.47

Più

-0.45

theless

-0.45

embar

-0.45

umman

-0.44

POSITIVE LOGITS

 namely

0.99

namely

0.92

那就是

0.82

 Namely

0.79

 yaitu

0.74

viz

0.72

الإنجليزية

0.71

 nemlig

0.71

yaitu

0.68

memoized

0.67

Activations Density 0.353%

references to specific examples or clarifications within a discussion

No Comments

No Known Activations