INDEX

Explanations

hospital-related terms and locations

oai_token-act-pair · gpt-3.5-turbo

terms related to healthcare and institutional settings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.84

ï¸ı

-0.84

cale

-0.79

atron

-0.78

yip

-0.75

erion

-0.74

iggurat

-0.72

peria

-0.71

emis

-0.71

nir

-0.68

POSITIVE LOGITS

 trips

0.95

 closures

0.93

 visits

0.92

 clos

0.90

goers

0.88

 clerks

0.88

 plac

0.88

 environments

0.87

 etiquette

0.86

 managers

0.85

Activations Density 0.360%

hospital-related terms and locations

terms related to healthcare and institutional settings

No Comments

No Known Activations