INDEX

Explanations

references to positions and dimensions in a structured data context

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

`x` followed by `)`

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

énario

-0.74

DebuggerNonUser

-0.69

]")]

-0.63

RenderAtEndOf

-0.61

 '\\;'

-0.61

 astore

-0.59

 "..\..\

-0.57

Diwedd

-0.57

DeleteBehavior

-0.56

IsContent

-0.56

POSITIVE LOGITS

%");

0.66

 NSCoder

0.63

Демографія

0.60

utilisons

0.60

.")

0.57

."));

0.56

 produisons

0.56

 cherchés

0.55

)")

0.54

ыгана

0.54

Activations Density 0.721%

references to positions and dimensions in a structured data context

`x` followed by `)`

No Comments

No Known Activations