INDEX

Explanations

words related to the name "Harvey"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "vey" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 lapse

-0.75

 supplementary

-0.70

Downloadha

-0.69

 vigilance

-0.67

phabet

-0.67

 dignity

-0.67

 derivatives

-0.66

 interior

-0.66

pires

-0.65

 increment

-0.63

POSITIVE LOGITS

ards

1.16

vey

1.07

age

0.86

rod

0.85

ors

0.85

rand

0.84

bugs

0.82

enegger

0.78

tons

0.78

kus

0.77

Activations Density 0.010%

words related to the name "Harvey"

occurrences of the word "vey" and its variations

No Comments

No Known Activations