INDEX

Explanations

hospital names

oai_token-act-pair · gpt-3.5-turbo

mentions of hospitals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

sig

-0.68

 totem

-0.66

 sage

-0.66

 counter

-0.64

nom

-0.64

 breaker

-0.64

 signal

-0.63

umen

-0.63

 beasts

-0.62

POSITIVE LOGITS

 Hospital

3.65

 Hosp

2.37

 hospital

2.27

 hospitals

2.07

hospital

2.06

ospital

1.95

 Medical

1.81

 Clinic

1.59

 Patients

1.59

 Surgery

1.58

Activations Density 0.006%

hospital names

mentions of hospitals

No Comments

No Known Activations