INDEX

Explanations

occurrences of significant actions and events within a narrative context

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

aggressive actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

WebControls

-0.44

 utafitiHapana

-0.43

DIPSETTING

-0.40

̈́

-0.36

attached

-0.35

exposed

-0.35

RTGC

-0.34

 Attached

-0.34

WriteBarrier

-0.34

 iNdEx

-0.33

POSITIVE LOGITS

useNewUrlParser

0.45

 favoured

0.45

 passing

0.43

getLogger

0.42

testing

0.42

Testing

0.42

 Passing

0.41

Passed

0.41

 penet

0.41

Agencies

0.41

Activations Density 0.124%

occurrences of significant actions and events within a narrative context

aggressive actions

No Comments

No Known Activations