INDEX

Explanations

prominent locations and significant landmarks in a context

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

 насељу

-0.98

aarrggbb

-0.97

 виправивши

-0.89

FormTagHelper

-0.88

ArrowToggle

-0.88

expandindo

-0.82

OGND

-0.79

parsedMessage

-0.76

 otomatig

-0.75

fjspx

-0.75

POSITIVE LOGITS

 Universidades

0.49

เข

0.48

thar

0.47

庁

0.47

 Seligman

0.47

ęs

0.46

 venuto

0.46

0.45

</h2>

0.45

0.44

Activations Density 0.127%

prominent locations and significant landmarks in a context

No Comments

No Known Activations