INDEX

Explanations

phrases indicating levels of risk or association with conditions, particularly in medical contexts

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

ніципалі

-0.49

TypedDataSet

-0.46

互联网档案馆

-0.44

ITER

-0.42

jeo

-0.41

onite

-0.40

 Travers

-0.40

umin

-0.40

 Lawson

-0.40

addGap

-0.39

POSITIVE LOGITS

 risk

3.24

risk

2.70

 risks

2.63

 Risk

2.58

Risk

2.50

 RISK

2.40

RISK

2.18

risks

2.15

 riesgo

2.13

 risked

2.11

Activations Density 0.442%

phrases indicating levels of risk or association with conditions, particularly in medical contexts

No Comments

No Known Activations