INDEX

Explanations

references to reading literature or books

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

addons

-0.73

Known

-0.71

 fitt

-0.71

 licens

-0.69

pmwiki

-0.63

 Ther

-0.62

htar

-0.62

 nicknamed

-0.60

FML

-0.60

 relocation

-0.60

POSITIVE LOGITS

×¨

0.74

aminer

0.70

×

0.69

 Quran

0.65

 poems

0.64

 sermon

0.64

Enough

0.63

 aloud

0.61

 congratulations

0.60

INTON

0.60

Activations Density 0.638%

references to reading literature or books

No Comments

No Known Activations