INDEX

Explanations

a frequent term or concept, specifically related to significant individuals or noteworthy events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

vlo

-0.61

Rule

-0.58

ne

-0.57

._

-0.54

poco

-0.53

<eos>

-0.51

so

-0.51

kirch

-0.51

 Rule

-0.51

POSITIVE LOGITS

AddTagHelper

1.09

Efq

0.99

)");

0.94

 itſelf

0.94

 raiſ

0.93

 Jefus

0.93

 becauſe

0.92

>");

0.90

)";

0.89

$.

0.89

Activations Density 0.111%

a frequent term or concept, specifically related to significant individuals or noteworthy events

No Comments

No Known Activations