INDEX

Explanations

references to specific entities or topics, particularly emphasizing formal structures or categorizations

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

Citations and references

np_acts-logits-general · gemini-2.0-flash

technical structures and data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-2.00

–

-1.30

（

-1.16

(!

-1.13

—

-1.10

-1.04

--

-1.00

—

-1.00

POSITIVE LOGITS

NUMX

1.16

Personendaten

1.14

writeFieldEnd

1.10

."]

1.08

SourceChecksum

1.06

WithIOException

1.05

TagMode

1.04

.")

1.01

.",

1.00

")));

0.99

Activations Density 0.574%

references to specific entities or topics, particularly emphasizing formal structures or categorizations

Citations and references

technical structures and data

No Comments

No Known Activations