INDEX

Explanations

references to health-related disclaimers or warnings

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

New Auto-Interp

Configuration

jbloom/GPT2-Small-OAI-v5-128k-attn-out-SAEs/v5_128k_layer_0

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

131,072

Data Type

torch.float32

Hook Name

blocks.0.hook_attn_out

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iliate

-0.83

ibility

-0.77

versions

-0.76

ilings

-0.73

luaj

-0.72

erers

-0.70

gements

-0.70

 cous

-0.69

 livest

-0.69

ãĤ¼

-0.68

POSITIVE LOGITS

atchewan

0.75

library

0.67

0.66

 Owners

0.65

asca

0.65

intendent

0.64

Klu

0.64

heter

0.63

BLIC

0.62

ÃĥÃĤ

0.62

Activations Density 0.091%

references to health-related disclaimers or warnings

No Comments

No Known Activations