INDEX

Explanations

sequences of symbols or comments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

%%%%%%%%%%%%%%%%

-0.65

Spoljašnje

-0.61

and

-0.58

────────

-0.53

****************

-0.52

but

-0.49

Hot

-0.49

at

-0.48

hot

-0.48

----------------

-0.47

POSITIVE LOGITS

IntoConstraints

0.92

 שוליים

0.89

 ExecuteAsync

0.82

évaluateur

0.74

!*\

0.74

enderror

0.74

StructEnd

0.74

SequentialGroup

0.73

titleMargin

0.71

 NSCoder

0.71

Activations Density 0.357%

sequences of symbols or comments in code

No Comments

No Known Activations