INDEX

Explanations

occurrences of specific key terms or phrases relevant to technical and specialized contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ränkt

-0.87

 Infórmanos

-0.84

Efq

-0.83

ọi

-0.82

lda

-0.82

 disambiguazione

-0.80

 poffe

-0.80

Cllr

-0.79

 الدولى

-0.79

modelBuilder

-0.79

POSITIVE LOGITS

 Hach

1.01

ách

1.00

0.96

ches

0.94

 PATCH

0.93

Rach

0.93

ich

0.93

Uch

0.93

 Rach

0.91

rach

0.91

Activations Density 0.294%

occurrences of specific key terms or phrases relevant to technical and specialized contexts

No Comments

No Known Activations