INDEX

Explanations

temporal references and indicators of current status or ongoing actions

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

now, currently, then

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

_=

-0.46

 taking

-0.45

 without

-0.44

==========

-0.44

new

-0.44

arrayOf

-0.43

withstanding

-0.43

thums

-0.42

 true

-0.42

的说道

-0.42

POSITIVE LOGITS

LabelTagHelper

0.65

avía

0.54

awtextra

0.53

 ſhe

0.52

Cuál

0.51

intervals

0.51

 Chrif

0.50

 Damit

0.49

ądze

0.48

 Grüsse

0.48

Activations Density 0.012%

temporal references and indicators of current status or ongoing actions

now, currently, then

No Comments

No Known Activations