INDEX

Explanations

phrases related to upcoming events or occasions

oai_token-act-pair · gpt-3.5-turbo

references to future events or releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

claimer

-0.89

imar

-0.88

lua

-0.82

lee

-0.80

istics

-0.77

ÃŃa

-0.77

sim

-0.75

andum

-0.74

ishing

-0.74

ifle

-0.73

POSITIVE LOGITS

 additions

0.92

 developments

0.90

 arrival

0.86

 installment

0.82

 arrivals

0.81

 schedule

0.79

 upcoming

0.79

 crop

0.77

 future

0.77

 occupant

0.76

Activations Density 0.011%

phrases related to upcoming events or occasions

references to future events or releases

No Comments

No Known Activations