INDEX

Explanations

scientific and mathematical terminology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ness

-1.17

-1.09

-1.00

-0.86

nya

-0.76

н

-0.74

ship

-0.72

<eos>

-0.71

م

-0.71

rd

-0.71

POSITIVE LOGITS

CME

1.16

CIE

1.14

DCE

1.08

CTE

1.07

NSE

1.07

SSE

1.07

eeeeeeee

1.06

 createSlice

1.06

MIME

1.05

Activations Density 1.619%

scientific and mathematical terminology

No Comments

No Known Activations