INDEX

Explanations

references to personal experiences and opinions regarding products and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

appearing

-0.52

appeared

-0.47

nabis

-0.47

盛り

-0.46

<%@

-0.45

 escor

-0.45

ablecer

-0.45

classnames

-0.44

cognition

-0.44

Executed

-0.43

POSITIVE LOGITS

complexContent

1.03

 buying

0.94

 nahilalakip

0.90

buy

0.89

 purchase

0.88

 purchasing

0.87

 bought

0.84

buy

0.83

ThroughAttribute

0.82

Buying

0.82

Activations Density 0.176%

references to personal experiences and opinions regarding products and services

No Comments

No Known Activations