INDEX

Explanations

terms and concepts related to biological and healthcare contexts

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Monfieur

-0.77

 ſeveral

-0.70

Efq

-0.70

 myſelf

-0.69

 houſe

-0.69

 themſelves

-0.67

 Neum

-0.67

 crdi

-0.67

 ExecuteAsync

-0.66

 ſche

-0.65

POSITIVE LOGITS

شهاد

0.61

Sucesor

0.56

StreetMap

0.55

UserScript

0.54

ori

0.53

userAgent

0.52

ja

0.52

googleapis

0.51

 uphold

0.51

ias

0.50

Activations Density 2.793%

terms and concepts related to biological and healthcare contexts

No Comments

No Known Activations