INDEX

Explanations

instances of legal actions, particularly involving arrests and jail sentences

oai_token-act-pair · gpt-3.5-turbo

phrases related to sentencing or legal consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

edin

-0.78

NET

-0.75

ieth

-0.75

soType

-0.72

atl

-0.72

soDeliveryDate

-0.71

net

-0.70

options

-0.70

ellen

-0.69

erd

-0.68

POSITIVE LOGITS

 violating

1.12

 breaching

1.04

geries

0.94

gery

0.92

 failing

0.90

bidden

0.90

 violations

0.86

 treason

0.85

 lack

0.84

 daring

0.82

Activations Density 0.118%

instances of legal actions, particularly involving arrests and jail sentences

phrases related to sentencing or legal consequences

No Comments

No Known Activations