INDEX

Explanations

references to the telnet protocol and associated terms

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

words starting with "tel"

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

evos

-0.54

mannian

-0.53

 Italijanski

-0.52

 للاسماء

-0.52

owan

-0.52

++

-0.52

#--

-0.51

ȼ

-0.51

gus

-0.51

 '\\;'

-0.49

POSITIVE LOGITS

Tel

1.02

Tel

0.99

TEL

0.94

tel

0.82

TEL

0.76

 Tél

0.68

tel

0.67

 Telephone

0.66

 tell

0.64

 Tell

0.64

Activations Density 0.004%

references to the telnet protocol and associated terms

words starting with "tel"

No Comments

No Known Activations