INDEX

Explanations

words related to medical institutions, such as hospitals and universities with medical programs

oai_token-act-pair · gpt-3.5-turbo

references to medical institutions and their associated activities

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

ibly

-0.91

hered

-0.78

IBLE

-0.76

inventoryQuantity

-0.74

verted

-0.72

èª

-0.72

posted

-0.71

oise

-0.71

ibles

-0.71

urous

-0.70

POSITIVE LOGITS

 Madness

0.97

 Solutions

0.92

 Association

0.91

 Corps

0.90

 Library

0.89

 Unit

0.89

 Massacre

0.88

 Authority

0.88

Aid

0.88

 Mayhem

0.88

Activations Density 0.072%

words related to medical institutions, such as hospitals and universities with medical programs

references to medical institutions and their associated activities

No Comments

No Known Activations