INDEX

Explanations

connections and associations between people, events, or entities in a legal or investigative context

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

 Roskov

-0.57

 abur

-0.51

ItemBackground

-0.50

gale

-0.49

idum

-0.49

PyExc

-0.49

DBNull

-0.48

 MediatR

-0.47

뀜

-0.47

umbar

-0.46

POSITIVE LOGITS

 connection

2.33

 connections

2.13

 link

1.92

 links

1.87

 Connection

1.81

 ties

1.78

 connects

1.77

 connect

1.76

connection

1.76

 linkage

1.75

Activations Density 0.536%

connections and associations between people, events, or entities in a legal or investigative context

No Comments

No Known Activations