INDEX

Explanations

terms related to processes or procedures

oai_token-act-pair · gpt-3.5-turbo

mentions of various processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

friends

-0.80

wings

-0.78

obar

-0.78

wich

-0.73

pants

-0.72

landers

-0.72

bane

-0.72

bucks

-0.70

jew

-0.70

stars

-0.69

POSITIVE LOGITS

 process

3.81

 processes

2.69

 Process

2.59

process

2.42

 procedure

1.98

Process

1.70

 PROC

1.56

 mechanism

1.44

 procedures

1.36

 processing

1.32

Activations Density 0.031%

terms related to processes or procedures

mentions of various processes

No Comments

No Known Activations