INDEX

Explanations

references to geographical locations and governmental entities

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

oprecip

-0.55

vstack

-0.54

correre

-0.51

ServletException

-0.46

 Pingback

-0.46

ringe

-0.45

Тогда

-0.45

beke

-0.45

daille

-0.44

enaar

-0.44

POSITIVE LOGITS

thâu

0.75

 समीक्षक

0.69

ngdoc

0.62

 noqa

0.61

 CreateTagHelper

0.60

VolleyError

0.59

UserScript

0.58

prefixer

0.57

expandindo

0.57

angliski

0.57

Activations Density 0.579%

references to geographical locations and governmental entities

No Comments

No Known Activations