INDEX

Explanations

terms related to research and academic analysis

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

 AssemblyCulture

-0.96

 '\\;'

-0.84

SerializedSize

-0.81

ThroughAttribute

-0.77

bewerken

-0.77

DockStyle

-0.77

 kaarangay

-0.75

 Taktlose

-0.75

 agrí

-0.72

cèse

-0.71

POSITIVE LOGITS

 known

0.42

 presentarse

0.41

 terci

0.41

 woven

0.41

 đề

0.41

 poseen

0.41

 reside

0.40

 solamente

0.40

key

0.40

 domain

0.40

Activations Density 0.573%

terms related to research and academic analysis

No Comments

No Known Activations