INDEX

Explanations

phrases related to the physical process of breathing or respiration

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "hal" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

URI

-0.79

 Veronica

-0.78

 Yankee

-0.75

 Cincinnati

-0.72

 Builder

-0.70

 Beyond

-0.69

 ANGEL

-0.69

llan

-0.69

ãĥ¼ãĥĨãĤ£

-0.67

 Sacrament

-0.67

POSITIVE LOGITS

ifax

1.08

uling

1.06

tering

1.03

ftime

0.99

ter

0.98

ibaba

0.98

enei

0.96

umph

0.96

icter

0.95

haul

0.91

Activations Density 0.015%

phrases related to the physical process of breathing or respiration

occurrences of the term "hal" in various contexts

No Comments

No Known Activations