INDEX

Explanations

references to trains and railroads

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Siro

-0.75

جوايز

-0.74

tory

-0.73

cstring

-0.71

gés

-0.70

ņas

-0.69

 Cuth

-0.68

Життєпис

-0.67

 DbContext

-0.67

SCAPE

-0.66

POSITIVE LOGITS

 train

2.10

 Train

2.07

 trains

1.97

 TRAIN

1.95

Train

1.90

 Trains

1.84

train

1.79

Trains

1.73

TRAIN

1.70

trains

1.67

Activations Density 0.053%

references to trains and railroads

No Comments

No Known Activations