INDEX

Explanations

language tags and properties in code or markup

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

__':

-1.01

 Monfieur

-0.98

 оригіналу

-0.96

 Majefty

-0.95

__":

-0.94

 preſent

-0.94

 pleaſure

-0.93

]';

-0.93

̈́

-0.93

 neceff

-0.90

POSITIVE LOGITS

lang

1.96

 Lang

1.85

 lang

1.82

Lang

1.67

 LANG

1.45

LANG

1.32

langs

1.08

 Langley

1.01

 Langer

0.80

 Langford

0.80

Activations Density 0.048%

language tags and properties in code or markup

No Comments

No Known Activations