INDEX

Explanations

negations and references to omissions or exclusions

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

Preceding tokens of "mention."

np_acts-logits-general · gemini-2.0-flash

mention or reference

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

 resourceCulture

-0.66

CompleteListener

-0.50

 Nacionales

-0.50

 Púb

-0.50

stdc

-0.49

ItemBackground

-0.48

 croire

-0.46

 compréhension

-0.46

 Jurí

-0.45

Accepted

-0.44

POSITIVE LOGITS

 mention

2.92

 mentions

2.48

 Mention

2.38

 mentioned

2.29

 mentioning

2.29

mention

2.22

Mention

2.19

 references

2.10

 reference

2.06

mentioned

1.99

Activations Density 0.671%

negations and references to omissions or exclusions

Preceding tokens of "mention."

mention or reference

No Comments

No Known Activations