INDEX

Explanations

statements involving assumptions and conditions in a theoretical context, particularly in mathematical or statistical discussions

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

followed by "assume" or "assumption"

np_acts-logits-general · gemini-2.0-flash

making assumptions

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

QMetaType

-0.47

нрави

-0.47

=(-

-0.47

chables

-0.47

[]:

-0.45

raje

-0.44

 Score

-0.44

██

-0.43

otient

-0.43

 }}"></

-0.43

POSITIVE LOGITS

 assumption

2.72

 assumptions

2.58

 assume

2.42

 assumed

2.39

assumption

2.26

 Assumptions

2.23

Assumption

2.17

 assumes

2.16

Assumptions

2.11

 assuming

2.08

Activations Density 1.186%

statements involving assumptions and conditions in a theoretical context, particularly in mathematical or statistical discussions

followed by "assume" or "assumption"

making assumptions

No Comments

No Known Activations