INDEX

Explanations

Additionally, this neuron looks for additional information or details

oai_token-act-pair · gpt-3.5-turbo

the word "Additionally" in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

-0.76

 Stockholm

-0.64

mos

-0.62

ends

-0.61

 Lyme

-0.61

fare

-0.60

olding

-0.60

 Fare

-0.60

agers

-0.59

orno

-0.59

POSITIVE LOGITS

 guiActiveUn

0.83

theless

0.80

atility

0.79

æ©Ł

0.79

wcs

0.78

Additionally

0.75

rehend

0.74

aredevil

0.69

essage

0.69

aeda

0.69

Activations Density 0.010%

Additionally, this neuron looks for additional information or details

the word "Additionally" in sentences

No Comments

No Known Activations