INDEX

Explanations

phrases indicating something is planned or scheduled to happen

oai_token-act-pair · gpt-3.5-turbo

phrases indicating planned future actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Perspective

-0.70

Shop

-0.66

Reader

-0.65

Kids

-0.64

 Teaching

-0.64

Tuc

-0.64

etheless

-0.63

 Checking

-0.63

 Reconstruction

-0.62

quickShipAvailable

-0.62

POSITIVE LOGITS

 expire

0.94

 coincide

0.88

be

0.82

pload

0.80

 eliminate

0.80

 yield

0.79

 intensify

0.79

NetMessage

0.78

 announce

0.78

 liberate

0.77

Activations Density 0.059%

phrases indicating something is planned or scheduled to happen

phrases indicating planned future actions or events

No Comments

No Known Activations