INDEX

Explanations

terms related to physical conditions 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 @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

DoubleQuotes

-0.84

DockStyle

-0.64

hésite

-0.64

lgari

-0.62

 Anglais

-0.61

TypedDataSet

-0.59

HostException

-0.57

 verlo

-0.56

MessageTagHelper

-0.55

 anglais

-0.55

POSITIVE LOGITS

 nahilalakip

0.61

+#+#

0.58

principalTable

0.55

garet

0.53

ineſs

0.52

 resourceCulture

0.52

 ostavi

0.51

ën

0.51

MarshalTo

0.50

Activations Density 0.396%

terms related to physical conditions and medical terminology

No Comments

No Known Activations