INDEX

Explanations

sections of text that introduce or highlight specific segments of information

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

Her

-0.48

Enllaces

-0.46

semb

-0.45

 lại

-0.45

 vuông

-0.45

 breaking

-0.44

InjectAttribute

-0.44

 Breaking

-0.43

 tháng

-0.43

<eos>

-0.42

POSITIVE LOGITS

 CreateTagHelper

0.94

tonode

0.93

évaluateur

0.87

 Paglinawan

0.73

Efq

0.72

 ་་

0.70

}{*}{}

0.70

يميديا

0.69

出版年

0.69

UVWXYZ

0.69

Activations Density 0.409%

sections of text that introduce or highlight specific segments of information

No Comments

No Known Activations