INDEX

Explanations

references to psychiatric disorders, particularly schizophrenia and related conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Lähteet

-0.64

 Himo

-0.62

 Roskov

-0.58

 terminée

-0.53

 Valenci

-0.51

 catar

-0.51

 SIMBAD

-0.51

 angiogenesis

-0.50

 sprocket

-0.50

 aeruginosa

-0.50

POSITIVE LOGITS

DSM

0.77

DSM

0.61

 Border

0.59

 manic

0.57

 Axis

0.56

 esboço

0.55

sch

0.55

 diagnos

0.55

BED

0.55

 comor

0.54

Activations Density 0.645%

references to psychiatric disorders, particularly schizophrenia and related conditions

No Comments

No Known Activations