INDEX

Explanations

commands or instructions related to software execution

oai_token-act-pair · gpt-3.5-turbo

terms related to executing commands or tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

este

-0.74

Î³

-0.66

iers

-0.63

 Alto

-0.62

aina

-0.61

kos

-0.60

FACE

-0.60

anton

-0.60

ijn

-0.59

 Greater

-0.59

POSITIVE LOGITS

 execute

1.01

 executes

0.96

 executing

0.93

 execution

0.87

eering

0.87

 executed

0.78

 executions

0.76

sequence

0.76

matically

0.74

Cmd

0.73

Activations Density 0.010%

commands or instructions related to software execution

terms related to executing commands or tasks

No Comments

No Known Activations