INDEX

Explanations

references to sockets in a technical context

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

socket

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

All

-0.51

 three

-0.49

all

-0.49

the

-0.48

 first

-0.47

-0.45

 five

-0.45

 main

-0.44

 Carl

-0.44

POSITIVE LOGITS

 Socket

1.25

Socket

1.15

 socket

1.14

socket

1.07

 sockets

0.96

SOCKET

0.88

sockets

0.87

Sockets

0.81

SequentialGroup

0.76

 websocket

0.71

Activations Density 0.007%

references to sockets in a technical context

socket

No Comments

No Known Activations