INDEX

Explanations

expressions related to lengths and sizes, particularly in a 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 @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Butterfield

-0.88

othesis

-0.81

ImagePath

-0.75

^^^^^^^^

-0.72

-0.71

 Hung

-0.69

 Bein

-0.68

thschild

-0.67

ſhip

-0.67

Erb

-0.67

POSITIVE LOGITS

len

1.71

len

1.71

Len

1.63

Len

1.54

LEN

1.39

LEN

1.19

 Lenny

1.08

 Lennox

1.07

 Elen

0.98

 Lenox

0.98

Activations Density 0.042%

expressions related to lengths and sizes, particularly in a programming context

No Comments

No Known Activations