INDEX

Explanations

identifiers related to medical conditions and their classifications

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

DockStyle

-0.69

TagMode

-0.65

 propOrder

-0.61

 وتسجيلات

-0.58

ActionCreators

-0.54

 GenerationType

-0.52

LLocation

-0.51

GenerationType

-0.49

princ

-0.49

 DriverManager

-0.49

POSITIVE LOGITS

RB

1.29

EB

1.29

CB

1.27

HB

1.27

IB

1.26

SB

1.26

WB

1.25

MB

1.24

RB

1.23

EB

1.23

Activations Density 0.812%

identifiers related to medical conditions and their classifications

No Comments

No Known Activations