INDEX

Explanations

philosophical words and concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to philosophical and ideological concepts

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

ivism

-0.95

trap

-0.82

rug

-0.78

ipt

-0.76

ramid

-0.76

ring

-0.75

rays

-0.75

redd

-0.75

lain

-0.74

iva

-0.74

POSITIVE LOGITS

 significance

0.96

 conflic

0.90

 prec

0.89

 objections

0.88

 impossibility

0.87

 referen

0.85

 prowess

0.85

 competence

0.85

 difficulties

0.85

 superiority

0.82

Activations Density 0.048%

philosophical words and concepts

terms related to philosophical and ideological concepts

No Comments

No Known Activations