INDEX

Explanations

terms related to locations and accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.92

sp

-0.84

en

-0.83

-0.82

-0.81

ac

-0.80

-0.75

-0.74

et

-0.74

POSITIVE LOGITS

 myſelf

1.30

 Anſ

1.25

 itſelf

1.23

 themſelves

1.18

ſelves

1.16

 Houſe

1.16

 leſs

1.13

 Monfieur

1.13

Efq

1.13

 purpoſe

1.12

Activations Density 0.050%

terms related to locations and accessibility

No Comments

No Known Activations