INDEX

Explanations

technical or programming terms related to coding and keyword specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

</h5>

-0.59

</u>

-0.55

-0.53

-0.49

ં

-0.47

</blockquote>

-0.47

</em>

-0.47

dit

-0.46

POSITIVE LOGITS

 CreateTagHelper

1.46

Personendaten

0.91

EndContext

0.82

 propOrder

0.81

WithIOException

0.80

 EconPapers

0.79

principalColumn

0.78

PYX

0.77

RenderAtEndOf

0.76

 nahilalakip

0.74

Activations Density 0.710%

technical or programming terms related to coding and keyword specifications

No Comments

No Known Activations