INDEX

Explanations

keywords related to buildings or structures

oai_token-act-pair · gpt-3.5-turbo

references to specific buildings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nir

-0.96

opard

-0.85

sha

-0.82

romeda

-0.78

 Nadu

-0.77

ican

-0.77

ï¸ı

-0.73

flix

-0.73

oni

-0.72

imum

-0.72

POSITIVE LOGITS

 renovations

1.02

 blocks

0.99

raper

0.98

 occupancy

0.98

Constructed

0.94

 erected

0.93

building

0.93

 constructed

0.93

 buildings

0.92

 renovation

0.91

Activations Density 0.040%

keywords related to buildings or structures

references to specific buildings

No Comments

No Known Activations