INDEX

Explanations

terms related to strategic changes or adjustments in a process or plan

oai_token-act-pair · gpt-3.5-turbo

key terms related to strategy and community engagement

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

Lan

-0.76

alcohol

-0.74

death

-0.70

Lee

-0.69

 corpses

-0.67

electric

-0.67

 impaired

-0.66

Blood

-0.66

 screams

-0.66

humans

-0.65

POSITIVE LOGITS

 pivot

3.94

piv

3.19

ivot

2.93

 outreach

1.26

 posture

0.99

 spokes

0.95

 hinge

0.94

 rotate

0.93

 diseng

0.92

Forward

0.91

Activations Density 0.027%

terms related to strategic changes or adjustments in a process or plan

key terms related to strategy and community engagement

No Comments

No Known Activations