INDEX

Explanations

words containing the "uns-" prefix

oai_token-act-pair · gpt-3.5-turbo

terms related to being "unsustainable" or "unsuitably" characterized scenarios

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SHIP

-0.76

 Dynamics

-0.70

tsky

-0.70

phrine

-0.69

eur

-0.68

 Nanto

-0.67

 Rams

-0.66

 drums

-0.65

 Guardians

-0.65

 Times

-0.65

POSITIVE LOGITS

olicited

1.28

aved

1.27

avour

1.21

atisf

1.21

killed

1.15

oci

1.14

ided

1.14

chool

1.13

ustain

1.13

iders

1.12

Activations Density 0.015%

words containing the "uns-" prefix

terms related to being "unsustainable" or "unsuitably" characterized scenarios

No Comments

No Known Activations