INDEX

Explanations

terms related to missions and stations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 OkHttpClient

-1.10

AccessorTable

-1.08

createServer

-1.03

]--;

-1.03

BagLayout

-1.01

CWE

-0.96

 parseFrom

-0.96

migrationBuilder

-0.92

haustible

-0.92

TPA

-0.92

POSITIVE LOGITS

ison

0.93

 station

0.89

 stations

0.89

 Station

0.85

ion

0.85

Station

0.84

ally

0.83

ary

0.83

lon

0.83

on

0.82

Activations Density 0.059%

terms related to missions and stations

No Comments

No Known Activations