INDEX

Explanations

references to types and classifications of entities, specifically in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Apro

-0.53

phemy

-0.53

ệc

-0.52

 endwhile

-0.51

ParallelGroup

-0.47

 PyObject

-0.47

tvguide

-0.46

mény

-0.46

ARL

-0.46

 valueOf

-0.45

POSITIVE LOGITS

StructEnd

0.69

 genre

0.62

 types

0.61

 fieldNum

0.61

 type

0.59

 calendriers

0.58

一種

0.54

types

0.54

évaluateur

0.54

 jenis

0.53

Activations Density 1.235%

references to types and classifications of entities, specifically in various contexts

No Comments

No Known Activations