INDEX

Explanations

references to molds and mold structures in descriptions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gms

-0.54

 Wikiseite

-0.53

estad

-0.53

hdashline

-0.53

 moindre

-0.52

iuo

-0.50

rý

-0.49

rste

-0.49

 crossorigin

-0.49

 testGet

-0.48

POSITIVE LOGITS

 mold

1.05

 Mushrooms

1.03

 mushrooms

1.00

 mushroom

0.98

Mushroom

0.96

 Mold

0.92

mold

0.89

mushroom

0.87

 Mushroom

0.86

TagHelper

0.85

Activations Density 0.101%

references to molds and mold structures in descriptions

No Comments

No Known Activations