INDEX

Explanations

references to barriers or divisions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.3.hook_attn_out

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.85

 guiActive

-0.74

icipated

-0.72

--------------------

-0.70

ãĤ¡

-0.67

restrial

-0.65

esan

-0.65

rett

-0.65

ICAN

-0.63

MON

-0.62

POSITIVE LOGITS

bery

0.65

 necks

0.62

rats

0.61

 cigars

0.60

 lungs

0.60

 cris

0.57

interstitial

0.57

rency

0.56

 bases

0.56

erers

0.56

Activations Density 0.066%

references to barriers or divisions in various contexts

No Comments

No Known Activations