INDEX

Explanations

references to ongoing or past experiences and responsibilities related to services

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

Following "have" or "has"

np_acts-logits-general · gemini-2.0-flash

verb 'have' forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 '\\;'

-0.76

ftagPool

-0.64

 ModelRenderer

-0.64

 eventdata

-0.64

ThroughAttribute

-0.63

+#+#

-0.62

 Wiktionnaire

-0.61

✨:

-0.59

RegressionTest

-0.58

 noce

-0.58

POSITIVE LOGITS

two

0.62

 offices

0.59

 three

0.58

 several

0.57

 four

0.56

offices

0.54

ReusableCell

0.53

 links

0.51

 five

0.50

subplots

0.49

Activations Density 0.184%

references to ongoing or past experiences and responsibilities related to services

Following "have" or "has"

verb 'have' forms

No Comments

No Known Activations