INDEX

Explanations

locations or references to place in a broad or abstract context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

initComponents

-0.76

 unknownFields

-0.73

-0.66

tis

-0.64

-0.63

ApiModelProperty

-0.63

 honor

-0.62

ry

-0.61

POSITIVE LOGITS

 anywhere

2.04

anywhere

2.00

 Anywhere

1.97

Anywhere

1.82

 Somewhere

1.79

 nowhere

1.78

 somewhere

1.76

somewhere

1.70

 Nowhere

1.70

 everywhere

1.67

Activations Density 0.082%

locations or references to place in a broad or abstract context

No Comments

No Known Activations