INDEX

Explanations

action verbs related to performance and outcomes

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

[Something] lends/speaks to [something]

np_acts-logits-general · gemini-2.0-flash

verbs followed by specific words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

InvalidProtocol

-0.65

TargetException

-0.62

myself

-0.59

 الحره

-0.59

andescent

-0.57

PasswordEncoder

-0.57

 AssemblyCulture

-0.57

HostException

-0.56

astify

-0.55

Становништво

-0.55

POSITIVE LOGITS

 itself

1.40

itself

1.08

 Itself

0.98

 nicely

0.85

us

0.85

 nothing

0.85

 perfectly

0.75

 quite

0.75

 beautifully

0.75

 greatly

0.75

Activations Density 0.644%

action verbs related to performance and outcomes

[Something] lends/speaks to [something]

verbs followed by specific words

No Comments

No Known Activations