INDEX

Explanations

technical terminology and references related to legal, medical, and procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

WithIOException

-0.85



-0.84

oa̍t

-0.81

enumii

-0.81

.*;

-0.78

 []).

-0.77

 EconPapers

-0.76

principalColumn

-0.74

[])

-0.71

tagHelperRunner

-0.71

POSITIVE LOGITS

0.98

 entanto

0.44

0.40

however

0.39

 angekommen

0.38

Vol

0.36

 obstante

0.36

 inoltre

0.36

 however

0.36

ècie

0.36

Activations Density 0.498%

technical terminology and references related to legal, medical, and procedural contexts

No Comments

No Known Activations