INDEX

Explanations

key navigation and directional commands 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 @ 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

ftagPool

-0.65

noscript

-0.58

 smtplib

-0.57

 referenties

-0.57

NewUrlParser

-0.53

cplusplus

-0.52

 subs

-0.52

DebuggerNonUser

-0.51

CardHeader

-0.51

 själva

-0.50

POSITIVE LOGITS

 direction

0.89

 downward

0.72

 directions

0.72

direction

0.69

 upward

0.69

 forward

0.67

 irány

0.67

forward

0.65

 Direction

0.65

wards

0.65

Activations Density 0.424%

key navigation and directional commands in a programming context

No Comments

No Known Activations