INDEX

Explanations

words related to memory and cognition

oai_token-act-pair · gpt-3.5-turbo

concepts related to memory and its types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

î

-0.73

 Carbuncle

-0.72

ãĢį

-0.69

prof

-0.66

_>

-0.63

profile

-0.63

cho

-0.62

Mic

-0.62

Iv

-0.61

VERTISEMENT

-0.61

POSITIVE LOGITS

unicip

0.77

 initials

0.70

ynt

0.70

 shortest

0.69

 subtract

0.68

 combining

0.67

 intentional

0.67

 leftover

0.67

 absorbed

0.67

itive

0.63

Activations Density 1.024%

words related to memory and cognition

concepts related to memory and its types

No Comments

No Known Activations