INDEX

Explanations

terms related to encoding and decoding processes

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

 Stoner

-0.73

viewpager

-0.72

DebuggerStep

-0.71

mitian

-0.69

 mView

-0.67

inghouse

-0.61

الحياه

-0.60

 تانيه

-0.60

 Figs

-0.60

 jButton

-0.59

POSITIVE LOGITS

 encode

2.37

encode

2.35

 Encode

2.17

 encoding

2.11

 encoded

2.06

 encodes

2.03

Encode

2.02

encoded

1.82

 Encoding

1.82

Encoding

1.72

Activations Density 0.127%

terms related to encoding and decoding processes

No Comments

No Known Activations