INDEX

Explanations

terms related to biological and bioengineering processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kaynağından

-1.02

 CreateTagHelper

-0.96

bootstrapcdn

-0.85

 Seizures

-0.82

yargs

-0.80

Elen

-0.79

 AssemblyCulture

-0.78

 Eller

-0.76

 linkovi

-0.75

 participle

-0.75

POSITIVE LOGITS

bio

1.74

Bio

1.66

BIO

1.49

Bio

1.48

bio

1.41

 bios

1.27

 био

1.21

 Biol

1.21

BIO

1.19

 Bios

1.11

Activations Density 0.151%

terms related to biological and bioengineering processes

No Comments

No Known Activations