INDEX

Explanations

legal terms related to claims for compensation or reparation

oai_token-act-pair · gpt-3.5-turbo

references to legal damages and compensation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

BOOK

-0.66

 Garner

-0.65

Bun

-0.65

 Schools

-0.63

KER

-0.63

 Handle

-0.62

 Merc

-0.62

ramid

-0.61

 Ident

-0.61

 Idle

-0.61

POSITIVE LOGITS

 damages

1.20

 damage

0.94

damage

0.85

 mitigation

0.82

uit

0.77

hiba

0.75

hooting

0.73

uits

0.73

 shocks

0.73

rays

0.73

Activations Density 0.010%

legal terms related to claims for compensation or reparation

references to legal damages and compensation in various contexts

No Comments

No Known Activations