INDEX

Explanations

action words related to planning, creating, and designing

oai_token-act-pair · gpt-3.5-turbo

words related to planning, creating, or formulating policies and legislation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

oil

-0.72

Mub

-0.65

istine

-0.63

hell

-0.62

inos

-0.62

pha

-0.60

ilty

-0.59

die

-0.59

oft

-0.59

 luck

-0.59

POSITIVE LOGITS

new

0.83

 elaborate

0.82

\\\\\\\\

0.79

 contingency

0.78

 alternate

0.76

 replacements

0.74

 customized

0.73

ulate

0.71

 solutions

0.71

ATIVE

0.71

Activations Density 0.233%

action words related to planning, creating, and designing

words related to planning, creating, or formulating policies and legislation

No Comments

No Known Activations