INDEX

Explanations

words related to peaks and peak counts in a statistical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

rungsseite

-0.76

 ujednoznacz

-0.68

MessageOf

-0.66

 Cours

-0.66

Fry

-0.65

)]$

-0.62

onymy

-0.62

 SURV

-0.61

 Pierson

-0.61

 Fré

-0.60

POSITIVE LOGITS

Tamil

0.77

 Tamil

0.72

 tamil

0.60

Kin

0.60

 peak

0.59

DN

0.59

TabIndex

0.58

wrapper

0.57

 Peak

0.56

elli

0.55

Activations Density 0.083%

words related to peaks and peak counts in a statistical context

No Comments

No Known Activations