INDEX

Explanations

verbs and nouns related to disintegration or dissolution.

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to dissociation

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

 Hunters

-0.71

 Pegasus

-0.69

eria

-0.67

liest

-0.66

 Month

-0.64

led

-0.64

 Trophy

-0.64

},"

-0.62

.","

-0.62

tailed

-0.62

POSITIVE LOGITS

 diss

3.98

 Diss

2.49

 dissent

1.57

 dissenting

1.41

 dissidents

1.38

 dissolution

1.25

 dissolve

1.22

 dissertation

1.17

 dissip

1.16

 defect

1.07

Activations Density 0.015%

**verbs and nouns related to disintegration or dissolution.**

terms and concepts related to dissociation

No Comments

No Known Activations

verbs and nouns related to disintegration or dissolution.