INDEX

Explanations

mathematical expressions and symbols, particularly those related to functions and inequalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

<eos>

-0.73

leurs

-0.63

↵↵↵↵

-0.63

 Johnston

-0.62

iotensin

-0.61

↵↵↵↵↵

-0.61

↵↵↵

-0.61

 Matos

-0.60

Johnston

-0.60

UTERS

-0.59

POSITIVE LOGITS

 esquerdo

0.89

 Tanto

0.74

Yud

0.72

 soigne

0.72

enumi

0.71

XB

0.70

 Budd

0.70

getColumnIndex

0.69

 kandang

0.69

 oorsp

0.69

Activations Density 0.371%

mathematical expressions and symbols, particularly those related to functions and inequalities

No Comments

No Known Activations