INDEX

Explanations

phrases related to power generation and energy sources

oai_token-act-pair · gpt-3.5-turbo

references to electricity generation and sources of power

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

romeda

-0.77

eryl

-0.75

Von

-0.73

ead

-0.71

Bei

-0.71

erella

-0.69

yll

-0.69

eret

-0.69

yip

-0.68

ean

-0.68

POSITIVE LOGITS

houses

1.19

 outage

0.98

 generators

0.98

 stations

0.96

station

0.93

 plants

0.90

boats

0.85

 grids

0.85

 consumption

0.85

plant

0.85

Activations Density 0.035%

phrases related to power generation and energy sources

references to electricity generation and sources of power

No Comments

No Known Activations