INDEX

Explanations

words related to memory triggers or associations

oai_token-act-pair · gpt-3.5-turbo

references to memories and recollections of experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ople

-0.81

IQ

-0.68

edin

-0.66

heading

-0.65

inery

-0.65

ucle

-0.64

OPLE

-0.63

ieved

-0.62

TB

-0.62

oct

-0.61

POSITIVE LOGITS

zsche

0.78

 vividly

0.75

 nostalg

0.73

 fond

0.73

 recall

0.72

 remember

0.72

 classic

0.71

how

0.71

 remembering

0.70

 srfAttach

0.68

Activations Density 0.050%

words related to memory triggers or associations

references to memories and recollections of experiences

No Comments

No Known Activations