INDEX

Explanations

references to names, especially in relation to fictional characters or entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

DockStyle

-0.68

modelBuilder

-0.59

addPreferredGap

-0.56

 שוליים

-0.54

️

-0.53

MigrationBuilder

-0.51

Ligações

-0.50

 lenker

-0.49

alism

-0.49

 насељу

-0.48

POSITIVE LOGITS

key

0.58

keted

0.58

KS

0.55

hael

0.55

 acid

0.52

hed

0.52

aksana

0.51

 reticulum

0.51

hes

0.51

hak

0.51

Activations Density 0.297%

references to names, especially in relation to fictional characters or entities

No Comments

No Known Activations