INDEX

Explanations

references to hospitals and related medical contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to institutions and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

yre

-0.72

 Dealer

-0.67

 Potion

-0.64

 Sensor

-0.62

 Jury

-0.62

itute

-0.61

thora

-0.60

ription

-0.60

 Applied

-0.60

aminer

-0.59

POSITIVE LOGITS

wide

1.41

goers

1.03

 insiders

0.98

 officials

0.87

 cohesion

0.87

members

0.86

 members

0.85

 employees

0.85

mates

0.84

 personnel

0.83

Activations Density 0.289%

references to hospitals and related medical contexts

terms related to institutions and organizations

No Comments

No Known Activations