INDEX

Explanations

references to product conditions and descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

principalTable

-0.61

-------------</

-0.60

ErrUnexpectedEOF

-0.55

featureID

-0.55

 Exactos

-0.54

homonymie

-0.53

ellees

-0.52

érfi

-0.52

rungsseite

-0.50

ografija

-0.50

POSITIVE LOGITS

 Excellent

0.71

Excellent

0.68

Exc

0.66

 excellent

0.66

 EXCELL

0.64

 overall

0.62

excellent

0.61

VG

0.60

Minor

0.58

 Good

0.58

Activations Density 0.156%

references to product conditions and descriptors

No Comments

No Known Activations