INDEX

Explanations

terms related to outcomes or results in various contexts

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

"result in"

np_acts-logits-general · gemini-2.0-flash

outcome

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ercito

-0.56

posedge

-0.56

BlockPos

-0.55

verter

-0.51

toContain

-0.49

hemiah

-0.48

moc

-0.48

ografija

-0.48

argli

-0.47

ہر

-0.46

POSITIVE LOGITS

 consequ

0.70

 unavoid

0.65

 inevitably

0.65

 resulted

0.64

 CreateTagHelper

0.63

 ultimately

0.60

}],

0.60

 into

0.59

]))

0.59

 Consequences

0.59

Activations Density 0.128%

terms related to outcomes or results in various contexts

"result in"

outcome

No Comments

No Known Activations