INDEX

Explanations

quantified numerical values and parameters

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

],

-0.58

];

-0.52

тивно

-0.48

$",

-0.46

ｮ

-0.46

];

-0.46

bov

-0.45

$}}

-0.45

|}{}

-0.44

POSITIVE LOGITS

AndEndTag

0.88

 оригіналу

0.87

bootstrapcdn

0.84

IntoConstraints

0.79

Попис

0.77

ItemBackground

0.77

AnchorStyles

0.73

ModelSerializer

0.72

 Jurí

0.71

troppo

0.71

Activations Density 0.269%

quantified numerical values and parameters

No Comments

No Known Activations