INDEX

Explanations

strings or phrases that are part of a structured configuration or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

횟

-0.57

 neutrals

-0.54

 hoof

-0.49

بوابة

-0.49

Eloquent

-0.48

 <>",

-0.48

VolleyError

-0.47

 monitors

-0.47

 propter

-0.47

 GeoNames

-0.46

POSITIVE LOGITS

帖最后由

0.96

numerusform

0.74

abestanden

0.74

 CreateTagHelper

0.65

bootstrapcdn

0.64

 تضيفلها

0.64

BeginContext

0.64

QRST

0.63

PreAuthorize

0.62

AddTagHelper

0.62

Activations Density 0.060%

strings or phrases that are part of a structured configuration or programming context

No Comments

No Known Activations