INDEX

Explanations

references to somatic symptoms and medical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.79

UnusedPrivate

-0.78

principalTable

-0.65

 برانيه

-0.60

antlr

-0.60

Kariera

-0.59

RequiresApi

-0.57

 høre

-0.57

på

-0.57

POSITIVE LOGITS

Erm

1.12

HAM

1.11

Dm

1.08

JIM

1.06

xm

1.06

JAM

1.03

DPM

1.02

HAM

1.02

Bm

1.02

Wim

1.01

Activations Density 3.177%

references to somatic symptoms and medical terminology

No Comments

No Known Activations