INDEX

Explanations

verbs related to accusing or blaming someone for something

oai_token-act-pair · gemini-2.0-flash

attempt/try

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__(/*!

-0.68

kmale

-0.61

esgue

-0.57

__":

-0.57

logg

-0.54

PhysRevLett

-0.53

buk

-0.53

 NSCoder

-0.53

-0.52

posedge

-0.52

POSITIVE LOGITS

 attempt

2.13

 attempts

2.00

try

1.88

 attempting

1.84

 tries

1.84

 Attempt

1.82

 trying

1.82

 attempted

1.81

try

1.80

 tried

1.80

Activations Density 2.586%

verbs related to accusing or blaming someone for something

attempt/try

No Comments

No Known Activations