INDEX

Explanations

phrases related to potential or possibility

oai_token-act-pair · gpt-3.5-turbo

conditional phrases that indicate potential outcomes or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

heid

-0.75

Vision

-0.69

cellence

-0.69

 queen

-0.68

rete

-0.66

fect

-0.64

chell

-0.63

mite

-0.62

iscovered

-0.61

olls

-0.61

POSITIVE LOGITS

 culmin

1.05

 equate

0.92

 coincide

0.92

 include

0.92

 coincides

0.91

 misunder

0.89

 resulted

0.88

 involve

0.88

 exacerbate

0.87

 necess

0.86

Activations Density 0.161%

phrases related to potential or possibility

conditional phrases that indicate potential outcomes or possibilities

No Comments

No Known Activations