INDEX

Explanations

terms related to anti-mental health treatment sentiments

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

references to antipsychotic medications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 anti

-1.23

anti

-1.02

 Anti

-0.77

 анти

-0.75

$_['

-0.75

Anti

-0.73

geslacht

-0.70

 <<<<<<<<<<<<<<

-0.66

]")]

-0.61

 ANTI

-0.60

POSITIVE LOGITS

AndEndTag

0.75

 Negra

0.72

IMPORTED

0.67

 resourceCulture

0.65

DoubleQuotes

0.61

yntaxException

0.60

Adri

0.59

pitaux

0.56

NOPQRST

0.54

PSP

0.54

Activations Density 0.114%

terms related to anti-mental health treatment sentiments

references to antipsychotic medications

No Comments

No Known Activations