INDEX

Explanations

concepts related to lack of control or regulation

oai_token-act-pair · gpt-3.5-turbo

terms related to lack of regulation, control, or oversight

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

otaur

-0.77

akov

-0.73

pty

-0.72

ixel

-0.70

azine

-0.70

orah

-0.69

arium

-0.68

esthetic

-0.66

aph

-0.66

estone

-0.66

POSITIVE LOGITS

paren

0.77

leased

0.75

 untreated

0.72

 unrestricted

0.70

Roaming

0.70

 unchecked

0.66

 Territories

0.65

 uncontrolled

0.63

 unaccompanied

0.62

 baggage

0.62

Activations Density 0.030%

concepts related to lack of control or regulation

terms related to lack of regulation, control, or oversight

No Comments

No Known Activations