INDEX

Explanations

references to agents in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 BeautifulSoup

-0.74

 Krie

-0.70

 bifurcation

-0.69

ERICK

-0.69

prehension

-0.69

ths

-0.68

 bifur

-0.68

endphp

-0.67

THS

-0.67

Thur

-0.66

POSITIVE LOGITS

 agents

1.84

 Agents

1.79

 agent

1.71

Agents

1.71

 Agent

1.67

 AGENT

1.65

agents

1.62

 AGENTS

1.62

Agent

1.62

AGENT

1.55

Activations Density 0.116%

references to agents in various contexts

No Comments

No Known Activations