INDEX

Explanations

terms related to patches and branching 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

DeclareMath

-0.68

tena

-0.63

awaiter

-0.63

 disambiguazione

-0.61

complexContent

-0.61

emer

-0.60

ella

-0.58

uarkan

-0.57

lüsse

-0.57

سته

-0.57

POSITIVE LOGITS

1.00

iness

0.97

hhhhhhhh

0.85

hhhh

0.84

intosh

0.74

hhh

0.74

lorette

0.73

hhhhh

0.71

 blanches

0.68

ptonshire

0.67

Activations Density 0.228%

terms related to patches and branching in various contexts

No Comments

No Known Activations